English
Related papers

Related papers: Learning to Linearize Deep Neural Networks for Sec…

200 papers

While deep learning has outperformed other methods for various tasks, theoretical frameworks that explain its reason have not been fully established. To address this issue, we investigate the excess risk of two-layer ReLU neural networks in…

Machine Learning · Statistics 2022-06-07 Shunta Akiyama , Taiji Suzuki

A low precision deep neural network training technique for producing sparse, ternary neural networks is presented. The technique incorporates hard- ware implementation costs during training to achieve significant model compression for…

Computer Vision and Pattern Recognition · Computer Science 2017-10-11 Julian Faraone , Nicholas Fraser , Giulio Gambardella , Michaela Blott , Philip H. W. Leong

In many recent works, multi-layer perceptions (MLPs) have been shown to be suitable for modeling complex spatially-varying functions including images and 3D scenes. Although the MLPs are able to represent complex scenes with unprecedented…

Computer Vision and Pattern Recognition · Computer Science 2023-07-04 Animesh Karnewar , Tobias Ritschel , Oliver Wang , Niloy J. Mitra

We prove that, for the fundamental regression task of learning a single neuron, training a one-hidden layer ReLU network of any width by gradient flow from a small initialisation converges to zero loss and is implicitly biased to minimise…

Machine Learning · Computer Science 2023-10-03 Dmitry Chistikov , Matthias Englert , Ranko Lazic

State-of-the-art sequential recommendation relies heavily on self-attention-based recommender models. Yet such models are computationally expensive and often too slow for real-time recommendation. Furthermore, the self-attention operation…

Information Retrieval · Computer Science 2023-11-09 Zhenrui Yue , Yueqi Wang , Zhankui He , Huimin Zeng , Julian McAuley , Dong Wang

In this paper, we consider the problem of automatically designing a Rectified Linear Unit (ReLU) Neural Network (NN) architecture that is sufficient to implement the optimal Model Predictive Control (MPC) strategy for an LTI system with…

Machine Learning · Computer Science 2019-11-06 James Ferlez , Yasser Shoukry

We consider a deep ReLU / Leaky ReLU student network trained from the output of a fixed teacher network of the same depth, with Stochastic Gradient Descent (SGD). The student network is \emph{over-realized}: at each layer $l$, the number…

Machine Learning · Computer Science 2020-06-30 Yuandong Tian

Privacy concerns in client-server machine learning have given rise to private inference (PI), where neural inference occurs directly on encrypted inputs. PI protects clients' personal data and the server's intellectual property. A common…

Machine Learning · Computer Science 2021-11-04 Karthik Garimella , Nandan Kumar Jha , Brandon Reagen

Deep Spiking Neural Networks (SNNs) present optimization difficulties for gradient-based approaches due to discrete binary activation and complex spatial-temporal dynamics. Considering the huge success of ResNet in deep learning, it would…

Neural and Evolutionary Computing · Computer Science 2022-01-25 Wei Fang , Zhaofei Yu , Yanqi Chen , Tiejun Huang , Timothée Masquelier , Yonghong Tian

Spoken language understanding (SLU) tasks involve mapping from speech audio signals to semantic labels. Given the complexity of such tasks, good performance might be expected to require large labeled datasets, which are difficult to collect…

Computation and Language · Computer Science 2022-07-12 Ankita Pasad , Felix Wu , Suwon Shon , Karen Livescu , Kyu J. Han

We study the problem of learning one-hidden-layer neural networks with Rectified Linear Unit (ReLU) activation function, where the inputs are sampled from standard Gaussian distribution and the outputs are generated from a noisy teacher…

Machine Learning · Statistics 2018-06-21 Xiao Zhang , Yaodong Yu , Lingxiao Wang , Quanquan Gu

The activation function is at the heart of a deep neural networks nonlinearity; the choice of the function has great impact on the success of training. Currently, many practitioners prefer the Rectified Linear Unit (ReLU) due to its…

Machine Learning · Computer Science 2021-08-24 Jordan Inturrisi , Sui Yang Khoo , Abbas Kouzani , Riccardo Pagliarella

Deep Linear and Nonlinear learning methods have already been vital machine learning methods for investigating the hierarchical features such as functional connectivity in the human brain via functional Magnetic Resonance signals; however,…

Machine Learning · Computer Science 2022-09-14 Wei Zhang , Yu Bao

We study the expressivity of ReLU neural networks in the setting of a binary classification problem from a topological perspective. Recently, empirical studies showed that neural networks operate by changing topology, transforming a…

Machine Learning · Computer Science 2024-06-12 Ekin Ergen , Moritz Grillo

We present a new approach for input optimization of ReLU networks that explicitly takes into account the effect of changes in activation patterns. We analyze local optimization steps in both the input space and the space of activation…

Machine Learning · Computer Science 2024-06-04 Hongzhan Yu , Sicun Gao

We introduce the "inverse square root linear unit" (ISRLU) to speed up learning in deep neural networks. ISRLU has better performance than ELU but has many of the same benefits. ISRLU and ELU have similar curves and characteristics. Both…

Machine Learning · Computer Science 2017-11-13 Brad Carlile , Guy Delamarter , Paul Kinney , Akiko Marti , Brian Whitney

The computation and storage requirements for Deep Neural Networks (DNNs) are usually high. This issue limits their deployability on ubiquitous computing devices such as smart phones, wearables and autonomous drones. In this paper, we…

Machine Learning · Computer Science 2017-02-28 Hande Alemdar , Vincent Leroy , Adrien Prost-Boucle , Frédéric Pétrot

In this paper, we focus on fully connected deep neural networks utilizing the Rectified Linear Unit (ReLU) activation function for nonparametric estimation. We derive non-asymptotic bounds that lead to convergence rates, addressing both…

Our community has greatly improved the efficiency of deep learning applications, including by exploiting sparsity in inputs. Most of that work, though, is for inference, where weight sparsity is known statically, and/or for specialized…

Machine Learning · Computer Science 2020-12-04 Zhangxiaowen Gong , Houxiang Ji , Christopher Fletcher , Christopher Hughes , Josep Torrellas

Large Language Models (LLMs) with billions of parameters have drastically transformed AI applications. However, their demanding computation during inference has raised significant challenges for deployment on resource-constrained devices.…