With this comprehensive breakdown of abstraction's multiple layers and components, we can understand and answer the question if abstraction is essential to artificial intelligence.
Lorenza Saitta, Università del Piemonte Orientale
Applying Innovation at different levels of abstractionJathish MJ
PCAPE Innovation aims to apply innovation at different levels of abstraction including business model innovations, functional or strategic innovations that redefine systems, and module level innovations.
Abstraction is a technique for arranging complexity of computer systems. It involves establishing a level of complexity and focusing only on details within that level. By focusing on a particular level of complexity, abstraction allows programmers to think clearly without concern for implementation details at other levels.
1) Embedded computing systems are programmable computers designed for specialized applications rather than general-purpose use. They are found in devices like cell phones, cars, appliances.
2) Early embedded systems date to the 1940s but microprocessors enabled more complex embedded applications starting in the 1970s. Modern vehicles can have over 100 microprocessors controlling various functions.
3) Embedded system design faces challenges like meeting deadlines, minimizing power consumption, and tight design timelines with small teams. Methodical design processes help address these challenges.
Gael Fraiteur argues that multithreaded programming needs to be addressed at the right level of abstraction, with design patterns like Actor, Immutable, Freezable, Thread Affine, Reader-Writer-Synchronized. Design patterns form a language and serve as a model against which code can be expressed. Compilers must support design patterns to allow code to be deterministically validated against the model, and of course to generate the low-level instructions that would be otherwise written manually.
Automation Abstraction Layers: Page Objects and BeyondAlan Richardson
An overview of different approaches to Page Objects and Domain Objects for GUI Automation. Examples use WebDriver and Java.
Full source code is available to download, For more details see the associated blog post.
Abstraction allows us to focus on essential details and suppress irrelevant details. It is one of the most important techniques for managing complexity in systems. There are five levels of abstraction in object-oriented programs ranging from viewing a program as interacting objects to considering individual methods in isolation. Forms of abstraction include specialization, division into parts, and multiple views. Understanding the history of abstraction mechanisms like procedures, modules, abstract data types, and objects provides context for object-oriented programming.
The document describes the design of an electrical stair climbing trolley. The key objectives were for it to carry up to 100kg, be comparable in cost and appearance to a conventional hand truck, and be easy to use. The initial design had issues but the final design uses a motor with a gear ratio, rechargeable batteries, and pulse width modulation for variable speed. Safety features, interchangeable parts, and a braking system were recommended to complete the design. The team was happy with their proposed design but encountered challenges that required iterative problem solving throughout the process.
Applying Innovation in Software DevelopmentAmish Gandhi
Sometimes the only difference between the winners and the losers is that the winners figure out how to innovate. Innovation is a broad term and this presentation outlines what it means for enterprises and companies involved in developing software. This presentation highlights how innovation can be applied at various stages of software product development and in different ways by applying special techniques, tools and frameworks.
Note: This was also a QCon Shanghai Keynote Talk. Full talk up at http://www.infoq.com/cn/presentations/business-innovation
Perpetual website: http://www.perpetualny.com
The document describes key components of software design including data design, architectural design, interface design, and procedural design. It discusses the goals of the design process which are to implement requirements, create an understandable guide for code generation and testing, and address implementation from data, functional, and behavioral perspectives. The document also covers concepts like abstraction, refinement, modularity, program structure, data structures, software procedures, information hiding, and cohesion and coupling.
Enhancing the Design pattern Framework of Robots Object Selection Mechanism -...INFOGAIN PUBLICATION
This document summarizes a research paper about developing a computer program that can take a 2D photograph as input, analyze it to determine the objects and their 3D structure, and output a 3D representation that can be viewed from any angle. The program makes assumptions about the objects, such as they are constructed from transformations of known 3D models and are supported by other visible objects or a ground plane. It develops processes for 2D to 3D construction and 3D to 2D display that can handle most arrangements of objects with planar surfaces.
This document proposes a quantitative approach to computing the image of a city. It begins by discussing how the image of a city is traditionally obtained through qualitative interviews. It then introduces concepts like legibility and imageability that contribute to a city's mental image. The core of the proposal is a multi-step process: 1) organizing city artifacts into layers, 2) ranking artifacts by size, 3) partitioning artifacts into "head" and "tail" groups using the mean size as the threshold, and 4) iteratively applying this partitioning until the distribution of large artifacts is no longer heavy-tailed. This process aims to capture the underlying "scaling pattern" common to cities where there are far more small artifacts than large ones. The
This document proposes methods for enhancing the visualization of concept lattices generated through formal concept analysis. It discusses extracting tree structures from concept lattices to improve readability. Various criteria are proposed for selecting parent concepts when transforming a lattice into a tree, including stability, support, shared attributes between concepts, and confidence. Visualization techniques like coloring nodes based on criteria values and sizing nodes by extent/intent ratios are also suggested to aid interpretation. The methods aim to make larger datasets more explorable by extracting simpler tree representations while preserving essential lattice features and structure.
This document summarizes a student paper about using the shortest path algorithm to interpolate contours in images. It discusses how the human visual system perceives 3D representations from 2D images and how extracting meaningful contours is challenging due to noise and discontinuities. The paper proposes using a modified Dijkstra's algorithm to find the shortest path in log-polar space, which maps circles in images to straight lines. This approach aims to identify simple, closed curves representing object contours while ignoring irrelevant edges.
Graphs and networks can be used to minimize project and product costs by determining the critical path and activities. The critical path method (CPM) identifies the longest path of activities in a project network to determine which activities are critical and cannot be delayed without extending the project duration. CPM is used to calculate the earliest and latest start times for activities. Identifying the critical path allows project managers to focus on reducing the time of critical path activities to minimize overall costs by reducing the project duration and resource needs. Network flow problems can also be modeled and solved using graphs and linear programming to determine the minimum cost of transporting products through a network from source to destinations.
This document provides an overview of topological quantum computing using anyons. It first discusses motivations for alternative computing approaches due to limitations of traditional computing. It then introduces braid theory, including definitions of braids and their equivalence. Braids form a braid group that can represent any braid as a word. Anyons are quasiparticles that emerge in 2D systems and can represent quantum bits in a way that is robust to environmental perturbations. Braids representing the trajectories of anyons over time can encode quantum information and computations in a topological manner.
This document presents a computational approach called "taskonomy" to model relationships and structure among visual tasks. It trains task-specific models on 26 visual tasks and computes transfer learning dependencies between tasks. This identifies which tasks provide useful information for other tasks. It finds the optimal transfer policy to solve tasks using limited labeled data, by leveraging relationships between tasks. For example, it shows 10 tasks can be solved using 2/3 less labeled data while maintaining performance, by transferring knowledge between related tasks.
The document discusses different levels of abstraction in object-oriented programming and design. It begins by defining abstraction and explaining why it is important for managing complexity. It then describes 5 levels of abstraction in OO programs from the highest level of interacting objects to the lowest level of individual methods. The document also covers different forms of abstraction like specialization and division into parts, and provides a brief history of abstraction mechanisms in computer science from assembly languages to modern object-oriented programming.
AR+S The Role Of Abstraction In Human Computer InteractionAli Rıza SARAL
The document provides an overview of the role of abstraction in human-computer interaction design. It discusses abstraction from cognitive and mathematical perspectives, and how abstraction helps reduce complexity and improve human performance. Models of human cognition like the multiple resources theory and discrete stages model are explained, along with concepts like Miller's theorem, workload, and situation awareness. The role of abstraction in interface design using techniques like menus, metaphors and chunking information is also covered.
International Journal of Engineering Inventions (IJEI) provides a multidisciplinary passage for researchers, managers, professionals, practitioners and students around the globe to publish high quality, peer-reviewed articles on all theoretical and empirical aspects of Engineering and Science.
This document provides an introduction to computational cubical homology. It begins by summarizing simplicial homology, including definitions of simplicial complexes, chains, and the boundary operator. It then introduces cubical homology, defining k-cubes, chains, and the cubical boundary operator. The document describes how computational homology uses linear algebra and the Smith normal form algorithm to compute homology groups. It concludes by discussing computational tools for homology and applications to image analysis and data science.
(DL輪読)Matching Networks for One Shot LearningMasahiro Suzuki
1. Matching Networks is a neural network architecture proposed by DeepMind for one-shot learning.
2. The network learns to classify novel examples by comparing them to a small support set of examples, using an attention mechanism to focus on the most relevant support examples.
3. The network is trained using a meta-learning approach, where it learns to learn from small support sets to classify novel examples from classes not seen during training.
AN GROUP BEHAVIOR MOBILITY MODEL FOR OPPORTUNISTIC NETWORKS csandit
Mobility is regarded as a network transport mechanism for distributing data in many networks.
However, many mobility models ignore the fact that peer nodes often carried by people and
thus move in group pattern according to some kind of social relation. In this paper, we propose
one mobility model based on group behavior character which derives from real movement
scenario in daily life. This paper also gives the character analysis of this mobility model and
compares with the classic Random Waypoint Mobility model.
Coates p: the use of genetic programming for applications in the field of spa...ArchiLab 7
This document summarizes two experiments using genetic programming to explore spatial composition and architectural form. The first experiment uses genetic programming to breed 3D solid and surface objects by evolving combinations of basic geometric primitives and transformations. The second experiment defines Le Corbusier's Domino House as a genetic program and evolves new variations by genetically manipulating additive and subtractive construction rules. The experiments demonstrate how genetic programming can be used to automatically generate and explore new architectural designs and spatial configurations.
This document describes research into making digital elevation models (DEMs) more interactive. It discusses how most DEM display programs only show surface contours or parallel profiles, without allowing addition of other data or direct interaction. The researchers developed a new concept where visibility is stored as a property of spatial units (points, triangles), rather than computed only for display. This allows functions like adding roads/buildings, querying point locations, and rotating the surface without recomputing visibility each time. It explains how this concept was implemented in their triangular irregular network (TIN) DEM system to compute visibility in stages and store intermediate results in the database.
The document discusses building conceptual models from sensor data by constructing networks that relate the data and looking for invariants within the network. Specifically, it proposes:
1) Building networks that relate sensor signals to each other using similarity measures.
2) Transporting information through the network using linear operators to relate function spaces.
3) Using network regularization and cycle consistency to find concepts that emerge as fixed points within the network.
ICPSR - Complex Systems Models in the Social Sciences - Lecture 3 - Professor...Daniel Katz
This document provides a summary of Stanley Milgram's small world experiment and discussion of complex network models. It discusses how Milgram found that the average path length between individuals in society is around 6 degrees of separation. Later work by Watts and Strogatz showed that networks with a small amount of randomness can display both clustering and small world properties. Degree distributions and other network measures like clustering coefficients and connected components are discussed. Preferential attachment models that generate power law degree distributions are presented.
CLIQUE is a grid-based clustering algorithm that identifies dense units in subspaces of high-dimensional data to provide efficient clustering. It works by first partitioning each attribute dimension into equal intervals and then the data space into rectangular grid cells. It finds dense units in subspaces like planes and intersections them to identify dense units in higher dimensions. These dense units are grouped into clusters. CLIQUE scales linearly with size of data and number of dimensions and automatically identifies relevant subspaces for clustering. However, the clustering accuracy may be reduced for simplicity.
Similar to Is Abstraction the Key to Artificial Intelligence? - Lorenza Saitta (20)
Liminal 360 is a Melbourne-based VR agency that created an interactive VR experience recreating the Coops Shot Tower in 1890s Melbourne. The temporary installation at Melbourne Central Shopping Center allowed over 3000 users to experience what the Shot Tower was like during its early years of operation, in collaboration with a local historian. Creating a smooth-running, glitch-free VR experience with constant lines of users posed challenges, but the project exceeded its goal of 1000 uses and provided valuable lessons for Liminal 360.
Engaging and sharing your VR experienceWithTheBest
The document is a presentation by @thatpatrickguy about engaging with and helping shape the future of virtual reality (VR). It provides a 4 step plan: 1) Get VR equipment and show it to others, 2) Make your own VR projects, 3) Connect with the VR community for help and collaboration, 4) Share your VR experiences, findings, and creations through blogging, public speaking, or other means. The presentation emphasizes that VR is still in early stages and can benefit from contributions from a diverse community of creators and early adopters.
How to survive the early days of VR as an Indie StudioWithTheBest
This document provides tips for indie VR studios to survive in the early days of VR by working for hire developing VR for other industries or developing their own intellectual properties. It encourages indie studios to survive in the early days of VR.
This document provides an overview of mixed reality technologies and experiences. It discusses how mixed reality can blend digital and physical worlds in a way that is convincing to the human perception system. The challenges of mixed reality include matching focal and vergence distances to avoid eye strain. As technologies improve and tools become more intuitive, mixed reality will allow unprecedented interactive digital content that is difficult to distinguish from the physical world. The document emphasizes thoughtful, experience-driven design that considers societal impacts and enhances human experiences.
Unlocking Human Potential with Immersive TechnologyWithTheBest
Virtual and augmented reality technologies have the potential to transform surgery, education, and improve human health and learning. VR allows surgeons to visualize complex procedures before operating to overcome limitations. It provides an immersive experience that enables surgeons to see inside the body and manipulate organs. These technologies may also transform education by creating engaging learning experiences that mimic real world scenarios. Overall, immersive technologies hold promise for enhancing human performance by giving people new ways to learn, train, and solve problems.
This document contains a list of 8 URLs from the website crowdoptic.com. The URLs reference files and folders related to projects, tests, and demonstrations involving crowdoptic, including ABC Pacers glass, crowdoptic clusters, curation, disruptsf, maplestestlarge, newsignal, zoom2, and jabberdemo.
Maximizing performance of 3 d user generated assets in unityWithTheBest
Maximizing performance of 3D user-generated assets in Unity
The document discusses optimizing 3D assets in Unity. It begins with an introduction and agenda, then covers optimization principles through examples from a trail renderer asset. The examples demonstrate reducing garbage collection by using queues instead of arrays, reusing components instead of creating new game objects, and comparing distances through dot products instead of taking square roots. Hands-on demonstrations are provided. Key takeaways are to profile for garbage collection, eliminate it by reusing objects when possible, and optimize comparisons.
This document discusses various methods for locomotion in virtual reality, including room-scale VR, teleportation, and treadmills. It proposes a new invention called ROVR, which is a low-friction dish and footwear that allows the user to walk naturally in VR without requiring much space. ROVR aims to provide an illusion of natural walking through simple leg movements while being affordable, portable, and avoiding issues with harness-based treadmills such as discomfort, restrictions to movement, and safety concerns. Evaluation of early ROVR prototypes showed promising results for applications in virtual tours, training, and gaming.
The document discusses haptic feedback in virtual reality using NullSpace VR's haptic suit. It covers best practices for creating haptic content including understanding the human body and timing, using reusable components, and creating complex effects through systems. NullSpace VR's suit has 16 haptic regions and supports Unity and Unreal. Their developer API allows for code-defined and file-defined haptics. The future of haptics is promising as integration improves.
How we use vr to break the laws of physicsWithTheBest
VR allows creators to break the laws of physics and create new worlds that would not be possible in reality. SightLine uses VR to transition scenes in bizarre and impossible ways without object permanence. The World of Comenius project uses VR to allow learning through experiments that would otherwise be too expensive, dangerous, or impossible. Neos provides a generic synchronization engine that makes any content automatically social and collaborative for VR classrooms. Neos: The Origin gives users superpowers to create procedurally generated worlds in a fun and natural way.
This document discusses the potential for virtual reality (VR) in various applications such as education, empathy, mental health, and research. VR allows users to feel truly present in virtual environments and feel connections to other people. It can be used to help people understand different cultures and perspectives. The document also describes several studies exploring using VR for medical training, treating depression and paranoia, and studying concepts like virtual body ownership.
You dont have to be mad to do VR and AR ... but it helpsWithTheBest
This document appears to be a list of names and companies related to virtual reality games. It includes Oscar Clark from Unity Technologies, followed by the names of several VR games and the studios that created them, including Dead & Buried (GunFire Games), SUPERHOT VR (SUPERHOT TEAM), I Expect You To Die (Schell Games), and Cosmic Trip (Funktronic Labs). It also includes a cryptic quote and email address for Oscar Clark.
OmniVirt is a platform that allows users to upload 360-degree virtual reality content once and have it distributed across all VR platforms and devices. It offers solutions for advertising VR content through display and video ads across mobile and desktop. It also hosts and distributes VR content through an HTML5 player and SDK that works across iOS, Android and desktop browsers. The platform aims to make it easy for brands and publishers to promote and distribute VR360 content more widely.
This document discusses human perception and interaction in virtual reality. It explains that VR hijacks the human perception-action system by providing distal stimuli (the virtual environment) and tracking human actions like head and hand movements as input. It describes several common interaction patterns used in VR like hand selection, pointing, image-plane selection, 3D multitouch, and 3D tool manipulation. Throughout development, iteration is important to refine VR interactions based on how users perceive and interact with the virtual environment.
Japheth Funding your startup - dating the devilWithTheBest
The document discusses different types of funding sources for startups, known as "the devils". It describes publishers, friends and family, angel investors, seed investors, venture capitalists, agencies, incubators, and accelerators. For each, it outlines what they provide, what they receive in return, what the founder gives up, and potential downsides. The document advises founders to pursue investors if they want a scalable business or publishers for a lifestyle business. It offers the accelerator program as a potential source of funding, mentorship, and business development deals.
Transported vr the virtual reality platform for real estateWithTheBest
We all know that buying a house is an emotional purchase. Facts and figures don’t sell houses. Imagination does. // A buyer walking through a home and imagining their new life there is the most powerful tool you can wield. // So how do we build virtual reality experiences that create walkthroughs that are a near perfect substitute for an in-person showing
Measuring Behavior in VR - Rob Merki Cognitive VRWithTheBest
This document discusses developer tools for analyzing virtual reality (VR) experiences. It notes that directing users is harder in VR than traditional media since VR is consumed actively. It outlines a three step process for VR analytics: 1) gather data on user behaviors and characteristics, 2) visualize VR sessions to see what users are doing, and 3) go beyond quantitative data to qualitative insights by seeing sessions from the user's perspective and identifying comfort issues. It introduces a new tool that provides quantitative, visual, and qualitative analytics with a single API call to help developers better understand user experiences.
Global demand for Mixed Realty (VR/AR) content is about to explode. WithTheBest
Commercial success depends upon the ability of VR producers to understand the complexities of creating and finishing, high-quality, content and finding an audience.
VR, a new technology over 40,000 years oldWithTheBest
Virtual Reality is at once both cutting edge, and a descendant of humanity's most ancient arts. Google's Chief Game Designer will bring some perspective to the origins of VR, why it matters to us in terms of evolution and storytelling, and give an overview of how Google is now supporting VR with tech like Google Cardboard, Android N, Daydream VR, and Spotlight Stories.
Garbage In, Garbage Out: Why poor data curation is killing your AI models (an...Zilliz
Enterprises have traditionally prioritized data quantity, assuming more is better for AI performance. However, a new reality is setting in: high-quality data, not just volume, is the key. This shift exposes a critical gap – many organizations struggle to understand their existing data and lack effective curation strategies and tools. This talk dives into these data challenges and explores the methods of automating data curation.
Finetuning GenAI For Hacking and DefendingPriyanka Aash
Generative AI, particularly through the lens of large language models (LLMs), represents a transformative leap in artificial intelligence. With advancements that have fundamentally altered our approach to AI, understanding and leveraging these technologies is crucial for innovators and practitioners alike. This comprehensive exploration delves into the intricacies of GenAI, from its foundational principles and historical evolution to its practical applications in security and beyond.
The History of Embeddings & Multimodal EmbeddingsZilliz
Frank Liu will walk through the history of embeddings and how we got to the cool embedding models used today. He'll end with a demo on how multimodal RAG is used.
"Hands-on development experience using wasm Blazor", Furdak Vladyslav.pptxFwdays
I will share my personal experience of full-time development on wasm Blazor
What difficulties our team faced: life hacks with Blazor app routing, whether it is necessary to write JavaScript, which technology stack and architectural patterns we chose
What conclusions we made and what mistakes we committed
Keynote : AI & Future Of Offensive SecurityPriyanka Aash
In the presentation, the focus is on the transformative impact of artificial intelligence (AI) in cybersecurity, particularly in the context of malware generation and adversarial attacks. AI promises to revolutionize the field by enabling scalable solutions to historically challenging problems such as continuous threat simulation, autonomous attack path generation, and the creation of sophisticated attack payloads. The discussions underscore how AI-powered tools like AI-based penetration testing can outpace traditional methods, enhancing security posture by efficiently identifying and mitigating vulnerabilities across complex attack surfaces. The use of AI in red teaming further amplifies these capabilities, allowing organizations to validate security controls effectively against diverse adversarial scenarios. These advancements not only streamline testing processes but also bolster defense strategies, ensuring readiness against evolving cyber threats.
Keynote : Presentation on SASE TechnologyPriyanka Aash
Secure Access Service Edge (SASE) solutions are revolutionizing enterprise networks by integrating SD-WAN with comprehensive security services. Traditionally, enterprises managed multiple point solutions for network and security needs, leading to complexity and resource-intensive operations. SASE, as defined by Gartner, consolidates these functions into a unified cloud-based service, offering SD-WAN capabilities alongside advanced security features like secure web gateways, CASB, and remote browser isolation. This convergence not only simplifies management but also enhances security posture and application performance across global networks and cloud environments. Discover how adopting SASE can streamline operations and fortify your enterprise's digital transformation strategy.
Increase Quality with User Access Policies - July 2024Peter Caitens
⭐️ Increase Quality with User Access Policies ⭐️, presented by Peter Caitens and Adam Best of Salesforce. View the slides from this session to hear all about “User Access Policies” and how they can help you onboard users faster with greater quality.
Choosing the Best Outlook OST to PST Converter: Key Features and Considerationswebbyacad software
When looking for a good software utility to convert Outlook OST files to PST format, it is important to find one that is easy to use and has useful features. WebbyAcad OST to PST Converter Tool is a great choice because it is simple to use for anyone, whether you are tech-savvy or not. It can smoothly change your files to PST while keeping all your data safe and secure. Plus, it can handle large amounts of data and convert multiple files at once, which can save you a lot of time. It even comes with 24*7 technical support assistance and a free trial, so you can try it out before making a decision. Whether you need to recover, move, or back up your data, Webbyacad OST to PST Converter is a reliable option that gives you all the support you need to manage your Outlook data effectively.
Cracking AI Black Box - Strategies for Customer-centric Enterprise ExcellenceQuentin Reul
The democratization of Generative AI is ushering in a new era of innovation for enterprises. Discover how you can harness this powerful technology to deliver unparalleled customer value and securing a formidable competitive advantage in today's competitive market. In this session, you will learn how to:
- Identify high-impact customer needs with precision
- Harness the power of large language models to address specific customer needs effectively
- Implement AI responsibly to build trust and foster strong customer relationships
Whether you're at the early stages of your AI journey or looking to optimize existing initiatives, this session will provide you with actionable insights and strategies needed to leverage AI as a powerful catalyst for customer-driven enterprise success.
It's your unstructured data: How to get your GenAI app to production (and spe...Zilliz
So you've successfully built a GenAI app POC for your company -- now comes the hard part: bringing it to production. Aparavi addresses the challenges of AI projects while addressing data privacy and PII. Our Service for RAG helps AI developers and data scientists to scale their app to 1000s to millions of users using corporate unstructured data. Aparavi’s AI Data Loader cleans, prepares and then loads only the relevant unstructured data for each AI project/app, enabling you to operationalize the creation of GenAI apps easily and accurately while giving you the time to focus on what you really want to do - building a great AI application with useful and relevant context. All within your environment and never having to share private corporate data with anyone - not even Aparavi.
What's New in Teams Calling, Meetings, Devices June 2024
Is Abstraction the Key to Artificial Intelligence? - Lorenza Saitta
1. Is Abstraction a
Key to Artificial
Intelligence?
Lorenza Saitta
Università del Piemonte Orientale
lorenza.saitta@uniupo.it
2. Premise
« Is abstraction a key to computing? »
[Kramer, 2007]
The same question can be posed for
Artificial Intelligence
« … [the process of] abstraction is the essence of
intelligence and the hard part of the problems being
solved »
[Brooks, 1991]
3. Representation
• Representation is critical in AI tasks
• Search for the “best” representation
• One that facilitates performing a task/solving a problem
• Often difficult to know a-priori which is the best
representation
• Expert definition on the basis of domain knowledge, experience,
analogy, …
• It is important to be able to easily change
representation when needed
• Several types of representation changes have been
proposed in AI à Abstraction is one of them
4. Abstraction = Cognitive Organizational Principle
• Abstraction is a special kind of representation change,
fundamental in human thinking
• Difficult to be precisely defined
• Abstraction aims at reducing the complexity of the
perceived world
« … a ubiquitous function of the cerebral
cortex, one in which many if not all of its areas
are involved, is that of abstraction »
[Zeki, 2009]
“Were it not for the ability to construct useful
abstraction, intelligent agents would be completely
swamped by the real world”
[Russel & Norvig, 2010]
5. Abstraction’s Modus Operandi (1)
• Focalization on relevant information and removal of
irrelevant details
• Aggregation/Grouping
Sciences, notably by Barsalou and co-workers, who provide a theoretical and
an experimental account of the issue [37]. An interesting connection can be
done with Computer Science, namely with the epistemological status of soft-
ware and the basic skills needed for writing good programs6. As a matter of
fact, Kramer wonders whether “abstraction is the key to computing” [272],
abstraction meaning here the capability of removing inessential details and to
identify a common “essence” inside variability.
This capability of going to the core of things is another fundamental aspect
attributed to abstraction, namely the ability to focus on relevance. Objects,
phenomena, events in the world are extremely rich in details and may be very
complex. However, when solving a problem or executing a task, only some
aspects of the reality are useful, and to take into consideration the whole wealth
of details may be confusing. For instance, when planning an aerial trip, the
physical attributes of the aircraft, such as color or exact shape and sizes, are
irrelevant and can be ignored. As another example, in Figure 1.3, a satellite
image of downtown Torino is reported, where the buildings and monuments can
be seen. However, just to find one’s way around the city it is more convenient
to reduce the information to the street network. By citing again Brooks [75],
“... abstraction is the essence of intelligence and the hard part of the problem
being solved”.
Stampa Invia LinkIndicazioni stradali Le mie mappeStampa Invia LinkIndicazioni stradali Le mie mappe
Fig. 1.3: Satellite image of the center of Torino (left): buildings and monuments are visible.
The same area can be described by considering just the street network (right): this abstract
map is more convenient for moving around the city.
Actually, in trying to solve a complex problem it may sometime be a good
strategy to proceed top-down, by starting with a coarse solution and then re-
fining it. At each step of refinement new details are possibly taken into account,
generating a sequence of solutions, each one more detailed than the previous
one. In this case we may speak of a hierarchy of levels of abstraction, with the
6
See Chapter 2.
Part–of
(bicycle)
Member-of
(forest) Functional relation
(computer, tennis set)
Computer
Keyboard
Mouse
Monitor
Body
Floppy
wheel
pedal
saddle handlebar
wheel
6. Abstraction’s Modus Operandi (2)
• Naming Equivalence classes of objects
• Discovery of new concepts
(predicate invention)
Chair =
Object with legs, a seat
and a back
Hub
Community
7. Abstraction’s Modus Operandi (3)
• Building Hierarchies
!
ules into a multilevel pyramid, as illustrated in Figure 1.
At each level, we describe the horizontal relationships
by a network of modules that is by itself the abstraction
of the network at a lower level [3]. In contrast, the verti-
cal relationships, shown as links between layers, repre-
sent the inclusion relationship between modules at
different levels. Using an abstraction pyramid, not only
can domain experts gain a global multilevel view of a
complex system from two different perspectives (hori-
zontal and vertical), but they can also investigate the
interconnection of the modules at a particular abstrac-
tion level of interest in the hierarchy.
abstraction pyramid discovered b
replace the known structure of on
Ontology (GO)), but instead provi
that may be missing. For example
mid identified from a protein-pr
work could illuminate the protein
levels. Some vertical or horizontal
vide additional biological meaning
acterized in the GO’s Directed A
structure.
We divide the analysis of comp
tasks: module discovery and mod
novelty of our two-way approach
synergy of top-down and bottom
rithms. This method identifies m
fashion and constructs a hierarchy
network from the bottom up. In
an abstraction of the network to d
ferent levels in the hierarchy.
divided into three procedures: (1)
mity between nodes; (2) extractin
the network, represented by a sp
partitioning the network based o
(3) generating an abstract network
ing the same procedures to a new
network, we can disclose an a
implied in a complex network. Th
provided in Figure 2 includes the f
Step 1. Input a given network o
Step 2. Calculate the proximit
nodes and use as the link weig
Step 3. Normalize the proxim
z-scores; then discard the links
a specified threshold to reduc
the network.
Step 4. Obtain the maximum-
from the network and use as th
Figure 1 Illustration of vertical and horizontal relationships.
Each circle represents a module. Vertical relationships and horizontal
relationships are denoted by dashed lines and solid lines,
respectively. The thickness of a solid line increases with the
importance of the connection. The original network is at the
bottom (Level 4). Higher-level networks are an abstraction, to a
certain degree, of the next lowest network.
Analysis of Biological Networks
[Cheng and Hu, 1997]
Level of Details (LOD) approach
[Luebke et al, 2003]
s-
C10,
organ
8. Abstraction supports Robust Descriptions
• Reduction of computational complexity
• Increasing in meaningfulness
Volume(x) ≤ a à Bike a < Volume(x) ≤ b à Car Volume(x) > b à Airplane
Has(two_wheels &
open-body & handelbar
& saddle)
-> Bicycle
Has(four_wheels &
body_with_windows)
-> Car
Has(retractable_wheels
& body & wings)
-> Airplane
Task-dependent
Reusable
10. Intensional Notion
122 5 Boundaries of Abstraction
Vehicle!
Land!
Vehicle!
Sea!
Vehicle!
Air!
Vehicle!
Good
transport!
People!
transport!
Cart!Truck! Bus! Train! Car! Bicycle!
…… ……!
AB#918#RS#
AH#708#SW#
BN#387#LG#
…………..#
is-a!
is-a!
is-a!
Instance-of!
is-a!
Fig. 5.2: A possible hierarchical organization of the concept vehicle = “thing used for
transporting people or goods”. Transportation may occur on land, sea, or air. A vehicle
Coverage
Abstraction
Abstraction ≠ Generalization
Less
informative
More
informative
More
general
Less
general
11. Relative Notion
again we do not know what to say: maybe there are important details that the
picture did not capture (for instance, the pistils), or the image is even too much
detailed (maybe, only the perception of a red field, as in impressionist art, would
matter). But, if we look at the picture in Fig. 5.4(b), and we compare picture
!"#$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$!%#$
Fig. 5.4: (a) Picture of a poppy field. If we only have this picture, it is impossible to say
whether it is concrete or abstract. (b) The same picture in black and white. By comparison,
this last is less informative than the colored one, because the information referring to the
color has been removed; then picture (b) is more abstract than picture (a). [A color version
Less abstract
More informative
(color information)
More abstract
Less informative
(no color information)
12. Path in an Abstraction Space
“Il vero modo et ordine per dissegnar tutte le parti ie
membra del corpo humano”,
[Fialetti , 1608]
5.1 Characteristic Aspects of Abstraction 127
Fig. 5.6: From Fialetti’s “Il vero modo et ordine per dissegnar tutte le parti ie membra del
corpo humano”, 1608. One among a set of studies for drawing eyes. ( c•
This artwork may
be protected by copyright. It is printed in this book in accordance with fair use principles.)
By taking the top-leftmost and bottom right-most drawings in Fig. 5.6, it
is really hard, without looking at the intermediate steps, to relate them in any
meaningful way. However, the relation between the two clearly appears if we
consider tho whole process of stepwise transformations.
Abstraction has been considered a process also in Mathematics, where the
concept of number is reached, according to Husserl, through a counting process
leaving aside all properties of a set of objects, except their numerosity. Lewis
[299] defines explicitly abstraction as a process of removing details from the
concrete5. Finally, Staub and Stern’s approach to abstraction6 mixes the idea
of abstraction as a process and abstraction as a relative notion, as we do; in
fact, these authors claim that concepts are obtained by reasoning, starting
from the concrete world. Along the reasoning chain abstraction increases, so
that the farther from the concrete world a concept is along the chain, the more
abstract. As an example, real numbers are more abstract than integers. Even
though this approach shares with our view the ideas of process and relativity
13. Path in an Abstraction Space
“Il vero modo et ordine per dissegnar tutte le parti ie
membra del corpo humano”,
[Fialetti , 1608]
5.1 Characteristic Aspects of Abstraction 127
Fig. 5.6: From Fialetti’s “Il vero modo et ordine per dissegnar tutte le parti ie membra del
corpo humano”, 1608. One among a set of studies for drawing eyes. ( c•
This artwork may
be protected by copyright. It is printed in this book in accordance with fair use principles.)
By taking the top-leftmost and bottom right-most drawings in Fig. 5.6, it
is really hard, without looking at the intermediate steps, to relate them in any
meaningful way. However, the relation between the two clearly appears if we
consider tho whole process of stepwise transformations.
Abstraction has been considered a process also in Mathematics, where the
concept of number is reached, according to Husserl, through a counting process
leaving aside all properties of a set of objects, except their numerosity. Lewis
[299] defines explicitly abstraction as a process of removing details from the
concrete5. Finally, Staub and Stern’s approach to abstraction6 mixes the idea
of abstraction as a process and abstraction as a relative notion, as we do; in
fact, these authors claim that concepts are obtained by reasoning, starting
from the concrete world. Along the reasoning chain abstraction increases, so
that the farther from the concrete world a concept is along the chain, the more
abstract. As an example, real numbers are more abstract than integers. Even
though this approach shares with our view the ideas of process and relativity
5.1 Characteristic Aspects of Abstraction 127
Fig. 5.6: From Fialetti’s “Il vero modo et ordine per dissegnar tutte le parti ie membra del
corpo humano”, 1608. One among a set of studies for drawing eyes. ( c•
This artwork may
be protected by copyright. It is printed in this book in accordance with fair use principles.)
Reversible path
Intermediate steps
can be recovered
14. Encapsulation
Q1 = “How many cars are there in the
line ?”
Details of the cars are hidden (they are
irrelevant to the question)
Q2 = “How many red cars are there in the line ?”
Details of the cars must be recoverable
Information is not lost, in the abstraction process, but only hidden,
shielded from the outside view
15. Abstraction Operators
All the operations described can be defined in terms of
Abstraction Operators
Input = I Output = O
O = ω(I,θ)Goldstone and Barsalou [1998]
Giunchiglia and Walsh [1992]
[Korf, 80]
Goldstone and Barsalou [1998]
Giunchiglia and Walsh [1992]
[Korf, 80]
img2 = Thresholding(img1,τ)
Operators are implemented via some algorithms
16. Signals vs Symbols
• Abstraction process always moves from richer, “low-level” descriptions
(concepts) toward “high-level” ones. During the process, only (hopefully)
information irrelevant to the current task is removed from view.
• In particular, abstraction establishes a link between signals (at the lowest
end of the spectrum) and symbols (at the highest end of the spectrum)
• Abstraction acts as a bridge between perceptual processing and symbolic
thinking. It tames the complexity of the sensory input, keeps the important
information, builds up intermediate concepts to reduce reasoning
complexity, and provides us with a re-organized view of the input, ready to
be interpreted in the light of our world model.
• We humans do not ascribe symbolic features to the sensory world, but we
receive raw inputs (images, sounds, …). On the other hand, we do not
interact with sets of weights, but with high level concepts and symbols
• Abstraction allows the early conflict in AI between numerical and symbolic
approaches to be overcome. Both signals and symbols become necessary and
cooperating aspects of both natural and artificial thinking.
17. Acquiring Abstractions
How are abstract operators acquired?
We do not know how we humans do it
Three levels of increasing difficulty
1. Given a set of predefined abstraction operators, we want to
choose the best suited to a given situation
• Usual approach in Machine Learning, Constraint Satisfaction problems,
Planning, Search, Problem Solving, ….
2. Learning an abstraction operator itself
• Some approach in Model-based Diagnosis, Constraint Satisfaction, Planning,
Machine Learning, …
• Deep learning
3. Meta-learning how an abstraction operator can be learned
• This is for the future
18. Deep Learning
Deep Learning
Data
acquisition
Learning
x f(X)
Feature
transformation
Feature
transformation
Feature
transformation
x z1
Classifier
f(X)z2
zh
…....
Intermediate representations
with increasing level of
abstraction and meaningfulness
(hopefully)
19. Learning Object Parts while Classifying
Groups of pixels (motifs) that
occur frequently are memorized
as features and reused in various
parts of an imageExamples of learned object parts from object categories
Learning object parts
Faces Cars Elephants Chairs
Classifier
Parts of objects
Segments
More complete parts of objects
Raw input
ω1
ω3
ω2
20. Local Receptive Fields
• Each feature can connect only to a small region of the lower layer
• (reduction in complexity)
• Similar regions are merged (they share the weights)
• The same features can be detected at different positions in the input
image
• Reduction in the number of free parameters
How can intermediate features be created?
Pooling
• Goal: Robust to local distortion
• Approach: Group similar features together
to achieve invariance
Aggregation
operator
Equivalence
operator
21. An Architecture for Abstraction
• Given a raw input (image, music,
written text, …) consisting of
elementary signals (pixels, sonds,
characters, ...), there are infinite
ways of forming sequences of
intermediate features. Deep learning
uses the output of classification to
select useful features (abstraction
operators, in our language). The
result is task-specific.
• We need a more general guiding
principle:
The best abstractions are those
tha are useful in the greater
number of different tasks
Head
Torso
Arm
Human
22. Evolution
• Multitasks Approach
• It is not possible to handle a large number of tasks at the same time
• A temporal dimension (evolution) has to be added
• A storage to keep the history of learning is necessary
LTM = Repository of
confirmed abstraction
operators and new
concepts
DLk
I O
ωk
1, …, ωk
n
STM ω
ωi
I O
DLh
ωh
1, …, ωh
m
LTM
ωj
ωk
Positive or
negative reinforcement
signal