English
Related papers

Related papers: Exponentially Increasing the Capacity-to-Computati…

200 papers

Recurrent neural networks are powerful models for processing sequential data, but they are generally plagued by vanishing and exploding gradient problems. Unitary recurrent neural networks (uRNNs), which use unitary recurrence matrices,…

Machine Learning · Statistics 2016-11-02 Scott Wisdom , Thomas Powers , John R. Hershey , Jonathan Le Roux , Les Atlas

Deeper and wider CNNs are known to provide improved performance for deep learning tasks. However, most such networks have poor performance gain per parameter increase. In this paper, we investigate whether the gain observed in deeper models…

Computer Vision and Pattern Recognition · Computer Science 2021-08-20 Arnav Chavan , Udbhav Bamba , Rishabh Tiwari , Deepak Gupta

Conventional wisdom in deep learning states that increasing depth improves expressiveness but complicates optimization. This paper suggests that, sometimes, increasing depth can speed up optimization. The effect of depth on optimization is…

Machine Learning · Computer Science 2018-06-12 Sanjeev Arora , Nadav Cohen , Elad Hazan

Recurrent neural networks (RNNs) are notoriously difficult to train. When the eigenvalues of the hidden to hidden weight matrix deviate from absolute value 1, optimization becomes difficult due to the well studied issue of vanishing and…

Machine Learning · Computer Science 2016-10-13 Martin Arjovsky , Amar Shah , Yoshua Bengio

A fundamental aspect of limitations in learning any computation in neural architectures is characterizing their optimal capacities. An important, widely-used neural architecture is known as autoencoders where the network reconstructs the…

Neurons and Cognition · Quantitative Biology 2017-05-23 Alireza Alemi , Alia Abbara

Neural networks and tree ensembles are state-of-the-art learners, each with its unique statistical and computational advantages. We aim to combine these advantages by introducing a new layer for neural networks, composed of an ensemble of…

Machine Learning · Computer Science 2020-07-14 Hussein Hazimeh , Natalia Ponomareva , Petros Mol , Zhenyu Tan , Rahul Mazumder

In this paper, we introduce a novel architecture for conditionally activated neural networks combining a hierarchical construction of multiple Mixture of Experts (MoEs) layers with a sampling mechanism that progressively converges to an…

Machine Learning · Computer Science 2025-02-21 Claudio Gallicchio , Giuseppe Nuti

Overparameterized models have proven to be powerful tools for solving various machine learning tasks. However, overparameterization often leads to a substantial increase in computational and memory costs, which in turn requires extensive…

Machine Learning · Computer Science 2024-03-13 Soo Min Kwon , Zekai Zhang , Dogyoon Song , Laura Balzano , Qing Qu

The complexity of deep neural network algorithms for hardware implementation can be lowered either by scaling the number of units or reducing the word-length of weights. Both approaches, however, can accompany the performance degradation…

Machine Learning · Computer Science 2016-11-22 Sungho Shin , Kyuyeon Hwang , Wonyong Sung

One of the distinguishing characteristics of modern deep learning systems is that they typically employ neural network architectures that utilize enormous numbers of parameters, often in the millions and sometimes even in the billions.…

Machine Learning · Statistics 2021-11-15 Ben Adlam , Jake Levinson , Jeffrey Pennington

This article summarizes principles and ideas from the emerging area of applying \textit{conditional computation} methods to the design of neural networks. In particular, we focus on neural networks that can dynamically activate or…

Machine Learning · Computer Science 2024-07-09 Simone Scardapane , Alessandro Baiocchi , Alessio Devoto , Valerio Marsocci , Pasquale Minervini , Jary Pomponi

Deep learning models are yielding increasingly better performances thanks to multiple factors. To be successful, model may have large number of parameters or complex architectures and be trained on large dataset. This leads to large…

Machine Learning · Computer Science 2022-12-20 Jean-Roch Vlimant , Junqi Yin

Deep Neural Networks are highly over-parameterized and the size of the neural networks can be reduced significantly after training without any decrease in performance. One can clearly see this phenomenon in a wide range of architectures…

Machine Learning · Computer Science 2018-06-19 Utku Evci

Recent advances in deep learning have made available large, powerful convolutional neural networks (CNN) with state-of-the-art performance in several real-world applications. Unfortunately, these large-sized models have millions of…

Machine Learning · Computer Science 2020-07-17 Giosuè Cataldo Marinò , Gregorio Ghidoli , Marco Frasca , Dario Malchiodi

Modern Neural Architecture Search methods have repeatedly broken state-of-the-art results for several disciplines. The super-network, a central component of many such methods, enables quick estimates of accuracy or loss statistics for any…

Machine Learning · Computer Science 2021-12-16 Kevin Alexander Laube , Andreas Zell

In machine learning, there is a fundamental trade-off between ease of optimization and expressive power. Neural Networks, in particular, have enormous expressive power and yet are notoriously challenging to train. The nature of that…

Machine Learning · Computer Science 2015-11-24 Diogo Almeida , Nate Sauder

We present a method that trains large capacity neural networks with significantly improved accuracy and lower dynamic computational cost. We achieve this by gating the deep-learning architecture on a fine-grained-level. Individual…

Machine Learning · Computer Science 2020-04-06 Babak Ehteshami Bejnordi , Tijmen Blankevoort , Max Welling

In comparison to classical shallow representation learning techniques, deep neural networks have achieved superior performance in nearly every application benchmark. But despite their clear empirical advantages, it is still not well…

Machine Learning · Computer Science 2022-01-11 Calvin Murdock , George Cazenavette , Simon Lucey

Neural Networks and Decision Trees: two popular techniques for supervised learning that are seemingly disconnected in their formulation and optimization method, have recently been combined in a single construct. The connection pivots on…

Machine Learning · Statistics 2020-02-27 Giuseppe Nuti , Lluís Antoni Jiménez Rugama , Kaspar Thommen

Predictive coding has emerged as an influential normative model of neural computation, with numerous extensions and applications. As such, much effort has been put into mapping PC faithfully onto the cortex, but there are issues that remain…

Neurons and Cognition · Quantitative Biology 2023-03-07 Siavash Golkar , Tiberiu Tesileanu , Yanis Bahroun , Anirvan M. Sengupta , Dmitri B. Chklovskii