English
Related papers

Related papers: Abstraction in Neural Networks

200 papers

Brain networks exhibit complications such as noise, neuron failures, and partial synaptic connectivity. These can make it difficult to model and analyze their behavior. This paper describes a way to address this difficulty, namely, breaking…

Data Structures and Algorithms · Computer Science 2025-03-25 Nancy Lynch

We describe how hierarchical concepts can be represented in three types of layered neural networks. The aim is to support recognition of the concepts when partial information about the concepts is presented, and also when some of the…

Neural and Evolutionary Computing · Computer Science 2025-03-25 Nancy A. Lynch

Abstraction is a key verification technique to improve scalability. However, its use for neural networks is so far extremely limited. Previous approaches for abstracting classification networks replace several neurons with one of them that…

Logic in Computer Science · Computer Science 2023-07-21 Calvin Chau , Jan Křetínský , Stefanie Mohr

Neural abstractions have been recently introduced as formal approximations of complex, nonlinear dynamical models. They comprise a neural ODE and a certified upper bound on the error between the abstract neural network and the concrete…

Logic in Computer Science · Computer Science 2023-10-03 Alec Edwards , Mirco Giacobbe , Alessandro Abate

The ability to abstract, count, and use System~2 reasoning are well-known manifestations of intelligence and understanding. In this paper, we argue, using the example of the ``Look and Say" puzzle, that although deep neural networks can…

Artificial Intelligence · Computer Science 2022-03-22 Wlodek W. Zadrozny

Mechanistic interpretability aims to reverse engineer neural networks by uncovering which high-level algorithms they implement. Causal abstraction provides a precise notion of when a network implements an algorithm, i.e., a causal model of…

Machine Learning · Computer Science 2025-03-17 Theodora-Mara Pîslar , Sara Magliacane , Atticus Geiger

Intensive research has been conducted on the verification and validation of deep neural networks (DNNs), aiming to understand if, and how, DNNs can be applied to safety critical applications. However, existing verification and validation…

Machine Learning · Computer Science 2021-03-08 Nicolas Berthier , Amany Alshareef , James Sharp , Sven Schewe , Xiaowei Huang

A longstanding problem for Deep Neural Networks (DNNs) is understanding their puzzling ability to generalize well. We approach this problem through the unconventional angle of \textit{cognitive abstraction mechanisms}, drawing inspiration…

Machine Learning · Computer Science 2020-04-20 Alex Gain , Hava Siegelmann

Deep Neural Networks (DNNs) are rapidly being applied to safety-critical domains such as drone and airplane control, motivating techniques for verifying the safety of their behavior. Unfortunately, DNN verification is NP-hard, with current…

Machine Learning · Computer Science 2020-09-15 Matthew Sotoudeh , Aditya V. Thakur

Whereas distributed computing research has been very successful in exploring the solvability/impossibility border of distributed computing problems like consensus in representative classes of computing models with respect to model…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-05-27 Hugo Rincon Galeana , Ulrich Schmid

A proper abstraction of a large-scale linear consensus network with a dense coupling graph is one whose number of coupling links is proportional to its number of subsystems and its performance is comparable to the original network. Optimal…

Systems and Control · Computer Science 2017-09-06 Milad Siami , Nader Motee

Despite significant advancements in post-hoc explainability techniques for neural networks, many current methods rely on heuristics and do not provide formally provable guarantees over the explanations provided. Recent work has shown that…

Machine Learning · Computer Science 2025-06-11 Shahaf Bassan , Yizhak Yisrael Elboher , Tobias Ladner , Matthias Althoff , Guy Katz

Abstraction is a powerful idea widely used in science, to model, reason and explain the behavior of systems in a more tractable search space, by omitting irrelevant details. While notions of abstraction have matured for deterministic…

Artificial Intelligence · Computer Science 2020-01-14 Vaishak Belle

Neural networks have demonstrated unmatched performance in a range of classification tasks. Despite numerous efforts of the research community, novelty detection remains one of the significant limitations of neural networks. The ability to…

Machine Learning · Computer Science 2022-05-03 Thomas A. Henzinger , Anna Lukina , Christian Schilling

The synergy between spiking neural networks and neuromorphic hardware holds promise for the development of energy-efficient AI applications. Inspired by this potential, we revisit the foundational aspects to study the capabilities of…

Neural and Evolutionary Computing · Computer Science 2024-03-18 Manjot Singh , Adalbert Fono , Gitta Kutyniok

Inspired by the brain, deep neural networks (DNN) are thought to learn abstract representations through their hierarchical architecture. However, at present, how this happens is not well understood. Here, we demonstrate that DNN learn…

Machine Learning · Computer Science 2015-02-16 Andrew J. R. Simpson

Network models describe the brain as sets of nodes and edges that represent its distributed organization. So far, most discoveries in network neuroscience have prioritized insights that highlight distinct groupings and specialized…

Neurons and Cognition · Quantitative Biology 2021-05-18 Joshua Faskowitz , Richard F. Betzel , Olaf Sporns

In abstractions of linear dynamic networks, selected node signals are removed from the network, while keeping the remaining node signals invariant. The topology and link dynamics, or modules, of an abstracted network will generally be…

Systems and Control · Electrical Eng. & Systems 2024-12-20 Harm H. M. Weerts , Jonas Linder , Martin Enqvist , Paul M. J. Van den Hof

High quality explanations of neural networks (NNs) should exhibit two key properties. Completeness ensures that they accurately reflect a network's function and interpretability makes them understandable to humans. Many existing methods…

Machine Learning · Computer Science 2025-03-20 Nolan Dey , Eric Taylor , Alexander Wong , Bryan Tripp , Graham W. Taylor

Deep neural networks (DNNs) have been shown lack of robustness for the vulnerability of their classification to small perturbations on the inputs. This has led to safety concerns of applying DNNs to safety-critical domains. Several…

Machine Learning · Computer Science 2021-02-24 Jianlin Li , Pengfei Yang , Jiangchao Liu , Liqian Chen , Xiaowei Huang , Lijun Zhang
‹ Prev 1 2 3 10 Next ›