Related papers: A Lightweight and Gradient-Stable Neural Layer
Understanding the generalization properties of neural networks on simple input-output distributions is key to explaining their performance on real datasets. The classical teacher-student setting, where a network is trained on data generated…
In this paper, we propose a novel Hadamard Transform (HT)-based neural network layer for hybrid quantum-classical computing. It implements the regular convolutional layers in the Hadamard transform domain. The idea is based on the HT…
This paper presents an implementation of multilayer feed forward neural networks (NN) to optimize CMOS analog circuits. For modeling and design recently neural network computational modules have got acceptance as an unorthodox and useful…
Artificial neural networks which are inspired from the learning mechanism of brain have achieved great successes in many problems, especially those with deep layers. In this paper, we propose a nucleus neural network (NNN) and corresponding…
Graph Neural Networks (GNNs) have emerged as a dominant paradigm for graph classification. Specifically, most existing GNNs mainly rely on the message passing strategy between neighbor nodes, where the expressivity is limited by the…
Recently, convolutional neural networks (CNNs) have set latest state-of-the-art on various human activity recognition (HAR) datasets. However, deep CNNs often require more computing resources, which limits their applications in embedded…
In many important graph data processing applications the acquired information includes both node features and observations of the graph topology. Graph neural networks (GNNs) are designed to exploit both sources of evidence but they do not…
Complex neural networks require substantial memory to store a large number of synaptic weights. This work introduces WINGs (Automatic Weight Generator for Secure and Storage-Efficient Deep Learning Models), a novel framework that…
The rapid proliferation of Deep Learning is increasingly constrained by its heavy reliance on high-performance hardware, particularly Graphics Processing Units (GPUs). These specialized accelerators are not only prohibitively expensive and…
Weight initialization remains decisive for neural network optimization, yet existing methods are largely layer-agnostic. We study initialization for deeply-supervised architectures with auxiliary classifiers, where untrained auxiliary heads…
In the realm of EEG decoding, enhancing the performance of artificial neural networks (ANNs) carries significant potential. This study introduces a novel approach, termed "weight freezing", that is anchored on the principles of ANN…
1 bit deep neural networks (DNNs), of which both the activations and weights are binarized , are attracting more and more attention due to their high computational efficiency and low memory requirement . However, the drawback of large…
We introduce a methodology for analyzing neural networks through the lens of layer-wise Hessian matrices. The local Hessian of each functional block (layer) is defined as the matrix of second derivatives of a scalar function with respect to…
Gradients of neural networks can be computed efficiently for any architecture, but some applications require differential operators with higher time complexity. We describe a family of restricted neural network architectures that allow…
In this work, we build a generic architecture of Convolutional Neural Networks to discover empirical properties of neural networks. Our first contribution is to introduce a state-of-the-art framework that depends upon few hyper parameters…
Recent progress in deep convolutional neural networks (CNNs) have enabled a simple paradigm of architecture design: larger models typically achieve better accuracy. Due to this, in modern CNN architectures, it becomes more important to…
Although considerable progress has been obtained in neural network quantization for efficient inference, existing methods are not scalable to heterogeneous devices as one dedicated model needs to be trained, transmitted, and stored for one…
While convolutional neural networks (CNNs) have recently made great strides in supervised classification of data structured on a grid (e.g. images composed of pixel grids), in several interesting datasets, the relations between features can…
In this paper we introduce ShiftCNN, a generalized low-precision architecture for inference of multiplierless convolutional neural networks (CNNs). ShiftCNN is based on a power-of-two weight representation and, as a result, performs only…
A neural architecture with randomly initialized weights, in the infinite width limit, is equivalent to a Gaussian Random Field whose covariance function is the so-called Neural Network Gaussian Process kernel (NNGP). We prove that a…