中文
相关论文

相关论文: Free energy of Bayesian Convolutional Neural Netwo…

200 篇论文

Artificial Neural Network (ANN)-based inference on battery-powered devices can be made more energy-efficient by restricting the synaptic weights to be binary, hence eliminating the need to perform multiplications. An alternative, emerging,…

机器学习 · 计算机科学 2020-12-16 Hyeryung Jang , Nicolas Skatchkovsky , Osvaldo Simeone

Neural networks (NN) have achieved state-of-the-art performance in various applications. Unfortunately in applications where training data is insufficient, they are often prone to overfitting. One effective way to alleviate this problem is…

机器学习 · 计算机科学 2016-11-03 Hao Wang , Xingjian Shi , Dit-Yan Yeung

While deeper convolutional networks are needed to achieve maximum accuracy in visual perception tasks, for many inputs shallower networks are sufficient. We exploit this observation by learning to skip convolutional layers on a per-input…

计算机视觉与模式识别 · 计算机科学 2018-07-26 Xin Wang , Fisher Yu , Zi-Yi Dou , Trevor Darrell , Joseph E. Gonzalez

Approximate Bayesian inference for neural networks is considered a robust alternative to standard training, often providing good performance on out-of-distribution data. However, Bayesian neural networks (BNNs) with high-fidelity…

机器学习 · 计算机科学 2021-12-07 Pavel Izmailov , Patrick Nicholson , Sanae Lotfi , Andrew Gordon Wilson

"How much energy is consumed for an inference made by a convolutional neural network (CNN)?" With the increased popularity of CNNs deployed on the wide-spectrum of platforms (from mobile devices to workstations), the answer to this question…

机器学习 · 计算机科学 2017-10-17 Ermao Cai , Da-Cheng Juan , Dimitrios Stamoulis , Diana Marculescu

Neural associative memories are single layer perceptrons with fast synaptic learning typically storing discrete associations between pairs of neural activity patterns. Previous works have analyzed the optimal networks under naive Bayes…

神经与进化计算 · 计算机科学 2024-12-25 Andreas Knoblauch

Bayesian neural networks (BNNs) combine the expressive power of deep learning with the advantages of Bayesian formalism. In recent years, the analysis of wide, deep BNNs has provided theoretical insight into their priors and posteriors.…

机器学习 · 计算机科学 2022-02-24 Beau Coker , Wessel P. Bruinsma , David R. Burt , Weiwei Pan , Finale Doshi-Velez

Convolutional Neural Networks (CNNs) filter the input data using spatial convolution operators with compact stencils. Commonly, the convolution operators couple features from all channels, which leads to immense computational cost in the…

机器学习 · 计算机科学 2019-05-17 Jonathan Ephrath , Lars Ruthotto , Eldad Haber , Eran Treister

We consider the problem of learning structures and parameters of Continuous-time Bayesian Networks (CTBNs) from time-course data under minimal experimental resources. In practice, the cost of generating experimental data poses a bottleneck,…

机器学习 · 统计学 2022-01-12 Dominik Linzner , Heinz Koeppl

Bayesian learning is built on an assumption that the model space contains a true reflection of the data generating mechanism. This assumption is problematic, particularly in complex data environments. Here we present a Bayesian…

机器学习 · 统计学 2018-11-05 S. P. Lyddon , S. G. Walker , C. C. Holmes

Deep neural network has been ensured as a key technology in the field of many challenging and vigorously researched computer vision tasks. Furthermore, classical ResNet is thought to be a state-of-the-art convolutional neural network (CNN)…

计算机视觉与模式识别 · 计算机科学 2024-09-02 Prathibha Varghese , G. Arockia Selva Saroja

Convolutional neural networks often dominate fully-connected counterparts in generalization performance, especially on image classification tasks. This is often explained in terms of 'better inductive bias'. However, this has not been made…

机器学习 · 计算机科学 2021-05-05 Zhiyuan Li , Yi Zhang , Sanjeev Arora

Convolutional neural networks (CNN) exhibit unmatched performance in a multitude of computer vision tasks. However, the advantage of using convolutional networks over fully-connected networks is not understood from a theoretical…

机器学习 · 计算机科学 2020-10-06 Eran Malach , Shai Shalev-Shwartz

Among the main features of biological intelligence are energy efficiency, capacity for continual adaptation, and risk management via uncertainty quantification. Neuromorphic engineering has been thus far mostly driven by the goal of…

神经与进化计算 · 计算机科学 2022-11-02 Nicolas Skatchkovsky , Hyeryung Jang , Osvaldo Simeone

We develop a novel data-driven approach to the inverse problem of classical statistical mechanics: given experimental data on the collective motion of a classical many-body system, how does one characterise the free energy landscape of that…

统计力学 · 物理学 2022-03-01 Peter Yatsyshin , Serafim Kalliadasis , Andrew B. Duncan

A well-trained Convolutional Neural Network can easily be pruned without significant loss of performance. This is because of unnecessary overlap in the features captured by the network's filters. Innovations in network architecture such as…

计算机视觉与模式识别 · 计算机科学 2019-02-26 Aaditya Prakash , James Storer , Dinei Florencio , Cha Zhang

Bayesian neural networks (BNNs) have recently regained a significant amount of attention in the deep learning community due to the development of scalable approximate Bayesian inference techniques. There are several advantages of using a…

机器学习 · 统计学 2023-05-02 Aliaksandr Hubin , Geir Storvik

Learning-based methods for inverse problems, adapting to the data's inherent structure, have become ubiquitous in the last decade. Besides empirical investigations of their often remarkable performance, an increasing number of works…

In the present era of deep learning, continual learning research is mainly focused on mitigating forgetting when training a neural network with stochastic gradient descent on a non-stationary stream of data. On the other hand, in the more…

机器学习 · 计算机科学 2024-05-30 Soochan Lee , Hyeonseong Jeon , Jaehyeon Son , Gunhee Kim

Standard Bayesian learning is known to have suboptimal generalization capabilities under misspecification and in the presence of outliers. PAC-Bayes theory demonstrates that the free energy criterion minimized by Bayesian learning is a…

机器学习 · 计算机科学 2023-04-25 Matteo Zecchin , Sangwoo Park , Osvaldo Simeone , Marios Kountouris , David Gesbert