English
Related papers

Related papers: Breaking Neural Network Scaling Laws with Modulari…

200 papers

Much as replacing hand-designed features with learned functions has revolutionized how we solve perceptual tasks, we believe learned algorithms will transform how we train models. In this work we focus on general-purpose learned optimizers…

Machine Learning · Computer Science 2020-09-24 Luke Metz , Niru Maheswaranathan , C. Daniel Freeman , Ben Poole , Jascha Sohl-Dickstein

Existing generalization measures that aim to capture a model's simplicity based on parameter counts or norms fail to explain generalization in overparameterized deep neural networks. In this paper, we introduce a new, theoretically…

Machine Learning · Computer Science 2021-03-11 Lorenz Kuhn , Clare Lyle , Aidan N. Gomez , Jonas Rothfuss , Yarin Gal

We study the phenomenon that some modules of deep neural networks (DNNs) are more critical than others. Meaning that rewinding their parameter values back to initialization, while keeping other modules fixed at the trained parameters,…

Machine Learning · Computer Science 2020-02-18 Niladri S. Chatterji , Behnam Neyshabur , Hanie Sedghi

The learned weights of a neural network have often been considered devoid of scrutable internal structure. In this paper, however, we look for structure in the form of clusterability: how well a network can be divided into groups of neurons…

Neural and Evolutionary Computing · Computer Science 2021-03-08 Daniel Filan , Stephen Casper , Shlomi Hod , Cody Wild , Andrew Critch , Stuart Russell

Training a single model on multiple input domains and/or output tasks allows for compressing information from multiple sources into a unified backbone hence improves model efficiency. It also enables potential positive knowledge transfer…

Machine Learning · Computer Science 2023-10-16 Amelie Royer , Tijmen Blankevoort , Babak Ehteshami Bejnordi

Studying the sensitivity of weight perturbation in neural networks and its impacts on model performance, including generalization and robustness, is an active research topic due to its implications on a wide range of machine learning tasks…

Machine Learning · Computer Science 2021-12-20 Yu-Lin Tsai , Chia-Yi Hsu , Chia-Mu Yu , Pin-Yu Chen

The optimal design of neural networks is a critical problem in many applications. Here, we investigate how dynamical systems with polynomial nonlinearities can inform the design of neural systems that seek to emulate them. We propose a…

Machine Learning · Computer Science 2021-06-23 Margaret Trautner , Ziwei Li , Sai Ravela

We perform an average case analysis of the generalization dynamics of large neural networks trained using gradient descent. We study the practically-relevant "high-dimensional" regime where the number of free parameters in the network is on…

Machine Learning · Statistics 2017-10-11 Madhu S. Advani , Andrew M. Saxe

Reinforcement learning (RL) can automate a wide variety of robotic skills, but learning each new skill requires considerable real-world data collection and manual representation engineering to design policy classes or features. Using deep…

Machine Learning · Computer Science 2016-09-23 Coline Devin , Abhishek Gupta , Trevor Darrell , Pieter Abbeel , Sergey Levine

We show that utilizing attribution maps for training neural networks can improve regularization of models and thus increase performance. Regularization is key in deep learning, especially when training complex models on relatively small…

Machine Learning · Computer Science 2022-05-31 Christian Tomani , Daniel Cremers

Deep learning relies on a very specific kind of neural networks: those superposing several neural layers. In the last few years, deep learning achieved major breakthroughs in many tasks such as image analysis, speech recognition, natural…

Artificial Intelligence · Computer Science 2018-02-01 Lê Nguyên Hoang , Rachid Guerraoui

Plasticity, the ability of a neural network to quickly change its predictions in response to new information, is essential for the adaptability and robustness of deep reinforcement learning systems. Deep neural networks are known to lose…

Machine Learning · Computer Science 2023-11-28 Clare Lyle , Zeyu Zheng , Evgenii Nikishin , Bernardo Avila Pires , Razvan Pascanu , Will Dabney

Neural scaling laws have revolutionized the design and optimization of large-scale AI models by revealing predictable relationships between model size, dataset volume, and computational resources. Early research established power-law…

Computation and Language · Computer Science 2025-05-28 Ayan Sengupta , Yash Goel , Tanmoy Chakraborty

We seek to improve deep neural networks by generalizing the pooling operations that play a central role in current architectures. We pursue a careful exploration of approaches to allow pooling to learn and to adapt to complex and variable…

Machine Learning · Statistics 2015-10-13 Chen-Yu Lee , Patrick W. Gallagher , Zhuowen Tu

Larger models learn tasks smaller models do not. What drives this phenomenon? We develop a simple phenomenological argument that power-law scaling already suggests that a larger model will be able to learn a part of the data distribution…

Planar graph drawings tend to be aesthetically pleasing. In this poster we explore a Neural Network's capability of learning various planar graph classes. Additionally, we also investigate the effectiveness of the model in generalizing…

Computational Geometry · Computer Science 2022-09-07 Smon van Wageningen , Tamara Mchedlidze

Scientific machine learning (ML) endeavors to develop generalizable models with broad applicability. However, the assessment of generalizability is often based on heuristics. Here, we demonstrate in the materials science setting that…

As deep neural networks (DNNs) achieve tremendous success across many application domains, researchers tried to explore in many aspects on why they generalize well. In this paper, we provide a novel perspective on these issues using the…

Machine Learning · Computer Science 2020-02-25 Jinlong Liu , Guoqing Jiang , Yunzhi Bai , Ting Chen , Huayan Wang

The method presented extends a given regression neural network to make its performance improve. The modification affects the learning procedure only, hence the extension may be easily omitted during evaluation without any change in…

Machine Learning · Computer Science 2016-12-07 Konrad Zolna

Deep learning algorithms demonstrate a surprising ability to learn high-dimensional tasks from limited examples. This is commonly attributed to the depth of neural networks, enabling them to build a hierarchy of abstract, low-dimensional…

Machine Learning · Computer Science 2024-07-04 Francesco Cagnetta , Leonardo Petrini , Umberto M. Tomasini , Alessandro Favero , Matthieu Wyart
‹ Prev 1 4 5 6 7 8 10 Next ›