English
Related papers

Related papers: Every Feedforward Neural Network Definable in an o…

200 papers

Wide neural networks have proven to be a rich class of architectures for both theory and practice. Motivated by the observation that finite width convolutional networks appear to outperform infinite width networks, we study scaling laws for…

Machine Learning · Computer Science 2020-08-21 Anders Andreassen , Ethan Dyer

We propose a scalable photonic architecture for implementation of feedforward and recurrent neural networks to perform the classification of handwritten digits from the MNIST database. Our experiment exploits off-the-shelf optical and…

Neural and Evolutionary Computing · Computer Science 2020-04-07 Piotr Antonik , Nicolas Marsal , Damien Rontani

We study computable probably approximately correct (CPAC) learning, where learners are required to be computable functions. It had been previously observed that the Fundamental Theorem of Statistical Learning, which characterizes PAC…

Machine Learning · Computer Science 2025-11-05 David Kattermann , Lothar Sebastian Krapp

We consider deep multi-layered generative models such as Boltzmann machines or Hopfield nets in which computation (which implements inference) is both recurrent and stochastic, but where the recurrence is not to model sequential structure,…

Machine Learning · Computer Science 2016-06-29 Yoshua Bengio , Benjamin Scellier , Olexa Bilaniuk , Joao Sacramento , Walter Senn

The use of Convolutional Neural Networks (CNNs) is widespread in Deep Learning due to a range of desirable model properties which result in an efficient and effective machine learning framework. However, performant CNN architectures must be…

Following the wide-spread adoption of machine learning models in real-world applications, the phenomenon of performativity, i.e. model-dependent shifts in the test distribution, becomes increasingly prevalent. Unfortunately, since models…

Machine Learning · Statistics 2026-01-21 Ivan Kirev , Lyuben Baltadzhiev , Nikola Konstantinov

We propose a novel multi-task learning architecture, which allows learning of task-specific feature-level attention. Our design, the Multi-Task Attention Network (MTAN), consists of a single shared network containing a global feature pool,…

Computer Vision and Pattern Recognition · Computer Science 2019-04-08 Shikun Liu , Edward Johns , Andrew J. Davison

The ability of overparameterized deep networks to generalize well has been linked to the fact that stochastic gradient descent (SGD) finds solutions that lie in flat, wide minima in the training loss -- minima where the output of the…

Machine Learning · Computer Science 2019-06-03 Vaishnavh Nagarajan , J. Zico Kolter

We present a formal and constructive framework for simulating Alternating Finite Automata (AFAs) using Logic-Gated Time-Shared Feedforward Networks (LG-TS-FFNs). Unlike prior neural automata models limited to Nondeterministic Finite…

Formal Languages and Automata Theory · Computer Science 2026-04-03 Sahil Rajesh Dhayalkar

Standard neural network architectures employ fixed activation functions (ReLU, tanh, sigmoid) that are poorly suited for approximating functions with singular or fractional power behavior, a structure that arises ubiquitously in physics,…

Machine Learning · Computer Science 2026-01-21 Gnankan Landry Regis N'guessan

We give algorithms with provable guarantees that learn a class of deep nets in the generative model view popularized by Hinton and others. Our generative model is an $n$ node multilayer neural net that has degree at most $n^{\gamma}$ for…

Machine Learning · Computer Science 2013-10-25 Sanjeev Arora , Aditya Bhaskara , Rong Ge , Tengyu Ma

Continual learning can incrementally absorb new concepts without interfering with previously learned knowledge. Motivated by the characteristics of neural networks, in which information is stored in weights on connections, we investigated…

Machine Learning · Computer Science 2023-06-21 Depeng Li , Tianqi Wang , Bingrong Xu , Kenji Kawaguchi , Zhigang Zeng , Ponnuthurai Nagaratnam Suganthan

Neural networks are widely used as a model for classification in a large variety of tasks. Typically, a learnable transformation (i.e. the classifier) is placed at the end of such models returning a value for each class used for…

Machine Learning · Computer Science 2021-03-30 Federico Pernici , Matteo Bruni , Claudio Baecchi , Alberto Del Bimbo

Sum-Product Networks (SPNs) can be regarded as a form of deep graphical models that compactly represent deeply factored and mixed distributions. An SPN is a rooted directed acyclic graph (DAG) consisting of a set of leaves (corresponding to…

Machine Learning · Computer Science 2020-02-27 Ishaq Aden-Ali , Hassan Ashtiani

In recent years, there has been growing interest in understanding neural architectures' ability to learn to execute discrete algorithms, a line of work often referred to as neural algorithmic reasoning. The goal is to integrate algorithmic…

Machine Learning · Computer Science 2026-02-16 Solveig Wittig , Antonis Vasileiou , Robert R. Nerem , Timo Stoll , Floris Geerts , Yusu Wang , Christopher Morris

Valiant's 1984 paper is widely credited with introducing the PAC learning model, but it, in fact, introduced a different model: unlike PAC learning, the learner receives only positives, may issue membership queries, and must output a…

Machine Learning · Statistics 2026-05-14 Steve Hanneke , Anay Mehrotra , Grigoris Velegkas , Manolis Zampetakis

The empirical success of deep learning is often attributed to deep networks' ability to exploit hierarchical structure in data, constructing increasingly complex features across layers. Yet despite substantial progress in deep learning…

Machine Learning · Computer Science 2026-01-28 Yunwei Ren , Yatin Dandi , Florent Krzakala , Jason D. Lee

Multi-layer feedforward networks have been used to approximate a wide range of nonlinear functions. An important and fundamental problem is to understand the learnability of a network model through its statistical risk, or the expected…

Machine Learning · Computer Science 2022-06-28 Gen Li , Jie Ding

The Universal Approximation Theorem (UAT) guarantees universal function approximation but does not explain how residual models distribute approximation across layers. We reframe residual networks as a layer-wise approximation process that…

Machine Learning · Computer Science 2026-04-28 Wei Wang , Xiao-Yong Wei , Qing Li

Fast linear algebra in deep learning usually comes with a choice: fixed geometry and exact computation, as in the Fourier transform, or adaptive geometry paid for by dense parameters, random features, or low-rank surrogates. To move beyond…

Machine Learning · Computer Science 2026-05-26 Łukasz Struski , Hanna Blazhko , Piotr Kubaty , Jacek Tabor