Related papers: Preserving Bilinear Weight Spectra with a Signed a…
In the era of large language models (LLMs), weight-activation quantization helps fit models on edge device by reducing memory and compute bit-widths. However, three challenges persist for energy constrained hardware: (1) even after…
In recent years, deep neural networks (DNNs) achieved unprecedented performance in many low-level vision tasks. However, state-of-the-art results are typically achieved by very deep networks, which can reach tens of layers with tens of…
Bearing fault diagnosis is of great importance to decrease the damage risk of rotating machines and further improve economic profits. Recently, machine learning, represented by deep learning, has made great progress in bearing fault…
This paper presents a data-driven approach, referred to as Quantized Skeletal Learning (QSL), for generating skeletal mechanisms. The approach has two key components: (1) a weight vector that can be used to eliminate relatively unimportant…
Gated Linear Units (GLU) have shown great potential in enhancing neural network performance. In this paper, I introduce a novel attention mechanism called GLU Attention, which introduces nonlinearity into the values of Attention. My…
Deep neural networks, and more recently large-scale generative models such as large language models (LLMs) and large vision-action models (LVAs), achieve remarkable performance across diverse domains, yet their prohibitive computational…
The scope of research in the domain of activation functions remains limited and centered around improving the ease of optimization or generalization quality of neural networks (NNs). However, to develop a deeper understanding of deep…
Binary Neural Networks emerged as a cost-effective and energy-efficient solution for computer vision tasks by binarizing either network weights or activations. However, common binary activations, such as the Sign activation function,…
This paper provides an analysis of state-of-the-art activation functions with respect to supervised classification of deep neural network. These activation functions comprise of Rectified Linear Units (ReLU), Exponential Linear Unit (ELU),…
Research in machine learning has successfully developed algorithms to build accurate classification models. However, in many real-world applications, such as healthcare, customer satisfaction, and environment protection, we want to be able…
The weight initialization and the activation function of deep neural networks have a crucial impact on the performance of the training procedure. An inappropriate selection can lead to the loss of information of the input during forward…
In recent years, neural networks have enjoyed a renaissance as function approximators in reinforcement learning. Two decades after Tesauro's TD-Gammon achieved near top-level human performance in backgammon, the deep reinforcement learning…
Existing works on the expressive power of neural networks typically assume real parameters and exact operations. In this work, we study the expressive power of quantized networks under discrete fixed-point parameters and inexact fixed-point…
Semi-structured networks (SSNs) merge the structures familiar from additive models with deep neural networks, allowing the modeling of interpretable partial feature effects while capturing higher-order non-linearities at the same time. A…
In past few years, linear rectified unit activation functions have shown its significance in the neural networks, surpassing the performance of sigmoid activations. RELU (Nair & Hinton, 2010), ELU (Clevert et al., 2015), PRELU (He et al.,…
Neural network acoustic models have significantly advanced state of the art speech recognition over the past few years. However, they are usually computationally expensive due to the large number of matrix-vector multiplications and…
Large Language Models (LLMs) have demonstrated exceptional proficiency in language-related tasks, but their deployment poses significant challenges due to substantial memory and storage requirements. Weight-only quantization has emerged as…
In this paper, a novel neural network activation function, called Symmetrical Gaussian Error Linear Unit (SGELU), is proposed to obtain high performance. It is achieved by effectively integrating the property of the stochastic regularizer…
Inference for state-of-the-art deep neural networks is computationally expensive, making them difficult to deploy on constrained hardware environments. An efficient way to reduce this complexity is to quantize the weight parameters and/or…
Computationally expensive neural networks are ubiquitous in computer vision and solutions for efficient inference have drawn a growing attention in the machine learning community. Examples of such solutions comprise quantization, i.e.…