Related papers: Supported-BinaryNet: Bitcell Array-based Weight Su…

The ability to learn continuously in artificial neural networks (ANNs) is often limited by catastrophic forgetting, a phenomenon in which new knowledge becomes dominant. By taking mechanisms of memory encoding in neuroscience (aka. engrams)…

Recent works on Binary Neural Networks (BNNs) have made promising progress in narrowing the accuracy gap of BNNs to their 32-bit counterparts. However, the accuracy gains are often based on specialized model designs using additional 32-bit…

This paper proposes a new algorithm based on multi-scale stochastic local search with binary representation for training neural networks. In particular, we study the effects of neighborhood evaluation strategies, the effect of the number of…

For fast and energy-efficient deployment of trained deep neural networks on resource-constrained embedded hardware, each learned weight parameter should ideally be represented and stored using a single bit. Error-rates usually increase when…

The memristive crossbar aims to implement analog weighted neural network, however, the realistic implementation of such crossbar arrays is not possible due to limited switching states of memristive devices. In this work, we propose the…

Deep neural networks are state-of-the-art models for understanding the content of images, video and raw input data. However, implementing a deep neural network in embedded systems is a challenging task, because a typical deep neural…

This paper studies the Binary Neural Networks (BNNs) in which weights and activations are both binarized into 1-bit values, thus greatly reducing the memory usage and computational complexity. Since the modern deep neural networks are of…

Binarization is an attractive strategy for implementing lightweight Deep Convolutional Neural Networks (CNNs). Despite the unquestionable savings offered, memory footprint above all, it may induce an excessive accuracy loss that prevents a…

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…

Big neural networks trained on large datasets have advanced the state-of-the-art for a large variety of challenging problems, improving performance by a large margin. However, under low memory and limited computational power constraints,…

Multiplication-less neural networks significantly reduce the time and energy cost on the hardware platform, as the compute-intensive multiplications are replaced with lightweight bit-shift operations. However, existing bit-shift networks…

In neural networks with binary activations and or binary weights the training by gradient descent is complicated as the model has piecewise constant response. We consider stochastic binary networks, obtained by adding noises in front of…

Artificial Neural Networks are connectionist systems that perform a given task by learning on examples without having prior knowledge about the task. This is done by finding an optimal point estimate for the weights in every node.…

Modeling natural phenomena with artificial neural networks (ANNs) often provides highly accurate predictions. However, ANNs often suffer from over-parameterization, complicating interpretation and raising uncertainty issues. Bayesian neural…

Deep neural networks (DNNs) have shown to provide superb performance in many real life applications, but their large computation cost and storage requirement have prevented them from being deployed to many edge and internet-of-things (IoT)…

Binarized Neural Networks (BNNs) significantly reduce the computation and memory demands with binarized weights and activations compared to full-precision NNs. Executing a layer in a BNN on different devices of a heterogeneous…

It is well-known that the high computational complexity and the insufficient samples in large-scale array signal processing restrict the real-world applications of the conventional full-dimensional adaptive beamforming (sample matrix…

Artificial Neural Networks (ANNs) are known as state-of-the-art techniques in Machine Learning (ML) and have achieved outstanding results in data-intensive applications, such as recognition, classification, and segmentation. These networks…

Multi-bit spiking neural networks (SNNs) have recently become a heated research spot, pursuing energy-efficient and high-accurate AI. However, with more bits involved, the associated memory and computation demands escalate to the point…

Quantized neural networks employ reduced precision representations for both weights and activations. This quantization process significantly reduces the memory requirements and computational complexity of the network. Binary Neural Networks…