English
Related papers

Related papers: On weight initialization in deep neural networks

200 papers

Single layer Feedforward Neural Network(FNN) is used many a time as a last layer in models such as seq2seq or could be a simple RNN network. The importance of such layer is to transform the output to our required dimensions. When it comes…

Machine Learning · Computer Science 2018-12-11 Vedanshu , M M Tripathi

Spiking Neural Networks (SNNs) and neuromorphic computing offer bio-inspired advantages such as sparsity and ultra-low power consumption, providing a promising alternative to conventional networks. However, training deep SNNs from scratch…

Computer Vision and Pattern Recognition · Computer Science 2025-05-21 Aurora Micheli , Olaf Booij , Jan van Gemert , Nergis Tömen

An artificial neuron is modelled as a weighted summation followed by an activation function which determines its output. A wide variety of activation functions such as rectified linear units (ReLU), leaky-ReLU, Swish, MISH, etc. have been…

Machine Learning · Computer Science 2019-12-30 Fayyaz ul Amir Afsar Minhas , Amina Asif

We propose the introduction of nonlinear operation into the feature generation process in convolutional neural networks. This nonlinearity can be implemented in various ways. First we discuss the use of nonlinearities in the process of data…

Machine Learning · Computer Science 2019-05-30 Gavneet Singh Chadha , Andreas Schwung

Tensorial Convolutional Neural Networks (TCNNs) have attracted much research attention for their power in reducing model parameters or enhancing the generalization ability. However, exploration of TCNNs is hindered even from weight…

Machine Learning · Computer Science 2022-07-26 Yu Pan , Zeyong Su , Ao Liu , Jingquan Wang , Nannan Li , Zenglin Xu

The interpretability of neural networks (NNs) is a challenging but essential topic for transparency in the decision-making process using machine learning. One of the reasons for the lack of interpretability is random weight initialization,…

Machine Learning · Computer Science 2021-03-01 Shohei Kubota , Hideaki Hayashi , Tomohiro Hayase , Seiichi Uchida

Continuous neural representations have recently emerged as a powerful and flexible alternative to classical discretized representations of signals. However, training them to capture fine details in multi-scale signals is difficult and…

Machine Learning · Computer Science 2022-10-06 Sifan Wang , Hanwen Wang , Jacob H. Seidman , Paris Perdikaris

Quantization and pruning are core techniques used to reduce the inference costs of deep neural networks. State-of-the-art quantization techniques are currently applied to both the weights and activations; however, pruning is most often…

Machine Learning · Computer Science 2021-11-02 Xinyu Zhang , Ian Colbert , Ken Kreutz-Delgado , Srinjoy Das

Neuron death is a complex phenomenon with implications for model trainability: the deeper the network, the lower the probability of finding a valid initialization. In this work, we derive both upper and lower bounds on the probability that…

Machine Learning · Computer Science 2021-06-14 Blaine Rister , Daniel L. Rubin

Loss of plasticity is a phenomenon in which a neural network loses its ability to learn when trained for an extended time on non-stationary data. It is a crucial problem to overcome when designing systems that learn continually. An…

Neural and Evolutionary Computing · Computer Science 2025-08-21 J. Fernando Hernandez-Garcia , Shibhansh Dohare , Jun Luo , Rich S. Sutton

We propose the Gaussian Error Linear Unit (GELU), a high-performing neural network activation function. The GELU activation function is $x\Phi(x)$, where $\Phi(x)$ the standard Gaussian cumulative distribution function. The GELU…

Machine Learning · Computer Science 2023-06-07 Dan Hendrycks , Kevin Gimpel

In this paper we investigate the performance of different types of rectified activation functions in convolutional neural network: standard rectified linear unit (ReLU), leaky rectified linear unit (Leaky ReLU), parametric rectified linear…

Machine Learning · Computer Science 2015-11-30 Bing Xu , Naiyan Wang , Tianqi Chen , Mu Li

We present some novel, straightforward methods for training the connection graph of a randomly initialized neural network without training the weights. These methods do not use hyperparameters defining cutoff thresholds and therefore remove…

Machine Learning · Computer Science 2020-11-18 Cristian Ivan , Razvan Florian

In feed-forward neural networks, dataset-free weight-initialization methods such as LeCun, Xavier (or Glorot), and He initializations have been developed. These methods randomly determine the initial values of weight parameters based on…

Machine Learning · Statistics 2025-11-13 Muneki Yasuda , Ryosuke Maeno , Chako Takahashi

We propose nonuniform data-driven parameter distributions for neural network initialization based on derivative data of the function to be approximated. These parameter distributions are developed in the context of non-parametric regression…

Machine Learning · Computer Science 2024-10-04 Konstantin Pieper , Zezhong Zhang , Guannan Zhang

The Rectified Power Unit (RePU) activation function, a differentiable generalization of the Rectified Linear Unit (ReLU), has shown promise in constructing neural networks due to its smoothness properties. However, deep RePU networks often…

Machine Learning · Computer Science 2026-02-10 Taeyoung Kim , Myungjoo Kang

We develop exact representations of training two-layer neural networks with rectified linear units (ReLUs) in terms of a single convex program with number of variables polynomial in the number of training samples and the number of hidden…

Machine Learning · Computer Science 2020-08-18 Mert Pilanci , Tolga Ergen

In neural networks, non-linearity is introduced by activation functions. One commonly used activation function is Rectified Linear Unit (ReLU). ReLU has been a popular choice as an activation but has flaws. State-of-the-art functions like…

Machine Learning · Computer Science 2021-12-23 Advait Vagerwal

We prove a large deviation principle for deep neural networks with Gaussian weights and at most linearly growing activation functions, such as ReLU. This generalises earlier work, in which bounded and continuous activation functions were…

Machine Learning · Statistics 2026-02-10 Quirin Vogel

We consider the computational complexity of training depth-2 neural networks composed of rectified linear units (ReLUs). We show that, even for the case of a single ReLU, finding a set of weights that minimizes the squared error (even…

Computational Complexity · Computer Science 2018-10-17 Pasin Manurangsi , Daniel Reichman
‹ Prev 1 4 5 6 7 8 10 Next ›