English
Related papers

Related papers: Improving Classification Neural Networks by using …

200 papers

Activation functions play an important role in training artificial neural networks. The majority of currently used activation functions are deterministic in nature, with their fixed input-output relationship. In this work, we propose a…

Weight quantization is one of the most important techniques of Deep Neural Networks (DNNs) model compression method. A recent work using systematic framework of DNN weight quantization with the advanced optimization algorithm ADMM…

Machine Learning · Computer Science 2019-05-03 Sheng Lin , Xiaolong Ma , Shaokai Ye , Geng Yuan , Kaisheng Ma , Yanzhi Wang

Neural networks are a powerful class of functions that can be trained with simple gradient descent to achieve state-of-the-art performance on a variety of applications. Despite their practical success, there is a paucity of results that…

Machine Learning · Computer Science 2017-03-06 Bo Xie , Yingyu Liang , Le Song

Binary Neural Networks (BNNs) have been garnering interest thanks to their compute cost reduction and memory savings. However, BNNs suffer from performance degradation mainly due to the gradient mismatch caused by binarizing activations.…

Machine Learning · Computer Science 2020-02-18 Hyungjun Kim , Kyungsu Kim , Jinseok Kim , Jae-Joon Kim

The step function is one of the simplest and most natural activation functions for deep neural networks (DNNs). As it counts 1 for positive variables and 0 for others, its intrinsic characteristics (e.g., discontinuity and no viable…

Machine Learning · Computer Science 2023-09-01 Hui Zhang , Shenglong Zhou , Geoffrey Ye Li , Naihua Xiu

Deep learning opacity often impedes deployment in high-stakes domains. We propose a training framework that aligns model focus with class-representative features without requiring pixel-level annotations. To this end, we introduce…

Artificial Intelligence · Computer Science 2026-02-16 Giacomo Ignesti , Davide Moroni , Massimo Martinelli

The internal states of most deep neural networks are difficult to interpret, which makes diagnosis and debugging during training challenging. Activation maximization methods are widely used, but lead to multiple optima and are hard to…

Computer Vision and Pattern Recognition · Computer Science 2018-12-12 Biye Jiang , David M. Chan , Tianhao Zhang , John F. Canny

Most deep neural networks use simple, fixed activation functions, such as sigmoids or rectified linear units, regardless of domain or network structure. We introduce differential equation units (DEUs), an improvement to modern neural…

Machine Learning · Computer Science 2019-05-21 MohamadAli Torkamani , Phillip Wallis , Shiv Shankar , Amirmohammad Rooshenas

We propose to optimize the activation functions of a deep neural network by adding a corresponding functional regularization to the cost function. We justify the use of a second-order total-variation criterion. This allows us to derive a…

Machine Learning · Statistics 2019-02-04 Michael Unser

The proper handling of out-of-distribution (OOD) samples in deep classifiers is a critical concern for ensuring the suitability of deep neural networks in safety-critical systems. Existing approaches developed for robust OOD detection in…

Computer Vision and Pattern Recognition · Computer Science 2024-06-18 Nasrin Alipour , Seyyed Ali SeyyedSalehi

It is well-known that overparametrized neural networks trained using gradient-based methods quickly achieve small training error with appropriate hyperparameter settings. Recent papers have proved this statement theoretically for highly…

Machine Learning · Computer Science 2020-04-13 Abhishek Panigrahi , Abhishek Shetty , Navin Goyal

We present empirical evidence that neural networks with ReLU and Absolute Value activations learn distance-based representations. We independently manipulate both distance and intensity properties of internal activations in trained models,…

Machine Learning · Computer Science 2024-11-28 Alan Oursland

We propose the Moderate Adaptive Linear Unit (MoLU), a novel activation function for deep neural networks, defined analytically as: f(x)=x \times (1+tanh(x))/2. MoLU combines mathematical elegance with empirical effectiveness, exhibiting…

Machine Learning · Computer Science 2025-07-16 Hankyul Koh , Joon-hyuk Ko , Wonho Jhe

In this paper, we introduce the Action Schema Network (ASNet): a neural network architecture for learning generalised policies for probabilistic planning problems. By mimicking the relational structure of planning problems, ASNets are able…

Artificial Intelligence · Computer Science 2017-12-25 Sam Toyer , Felipe Trevizan , Sylvie Thiébaux , Lexing Xie

Current research suggests that the key factors in designing neural network architectures involve choosing number of filters for every convolution layer, number of hidden neurons for every fully connected layer, dropout and pruning. The…

Machine Learning · Computer Science 2020-09-17 Himanshu Pradeep Aswani , Amit Sethi

The rectified linear unit (ReLU) is a highly successful activation function in neural networks as it allows networks to easily obtain sparse representations, which reduces overfitting in overparameterized networks. However, in network…

Machine Learning · Computer Science 2022-12-14 Shiyu Liu , Rohan Ghosh , Dylan Tan , Mehul Motani

Automatic Modulation Classification (AMC) is a signal processing technique widely used at the physical layer of wireless systems to enhance spectrum utilization efficiency. In this work, we propose a fast and accurate AMC system, termed…

Signal Processing · Electrical Eng. & Systems 2025-04-14 Faheem Ur Rehman , Qamar Abbas , M. Karam Shehzad

Many neural network architectures rely on the choice of the activation function for each hidden layer. Given the activation function, the neural network is trained over the bias and the weight parameters. The bias catches the center of the…

Machine Learning · Computer Science 2019-10-01 Farnoush Farhadi , Vahid Partovi Nia , Andrea Lodi

In recent years, the rapid development of deep learning has led to a wide range of applications in the field of medical image classification. The variants of neural network models with ever-increasing performance share some commonalities:…

Computer Vision and Pattern Recognition · Computer Science 2023-12-25 Wenhao Tang , Junding Sun , Shuihua Wang , Yudong Zhang

Adam is applied widely to train neural networks. Different kinds of Adam methods with different features pop out. Recently two new adam optimizers, AdaBelief and Padam are introduced among the community. We analyze these two adam optimizers…

Computer Vision and Pattern Recognition · Computer Science 2021-10-05 Zhaoyang Zhu , Haozhe Sun , Chi Zhang