Related papers: MeliusNet: Can Binary Neural Networks Achieve Mobi…
Although Convolutional Neural Networks (CNNs) achieve effectiveness in various computer vision tasks, the significant requirement of storage of such networks hinders the deployment on computationally limited devices. In this paper, we…
Existing Binary Neural Networks (BNNs) mainly operate on local convolutions with binarization function. However, such simple bit operations lack the ability of modeling contextual dependencies, which is critical for learning discriminative…
While the deployment of neural networks, yielding impressive results, becomes more prevalent in various applications, their interpretability and understanding remain a critical challenge. Network inversion, a technique that aims to…
Binary neural networks (BNNs) are an attractive solution for developing and deploying deep neural network (DNN)-based applications in resource constrained devices. Despite their success, BNNs still suffer from a fixed and limited…
In this work, we study the 1-bit convolutional neural networks (CNNs), of which both the weights and activations are binary. While being efficient, the classification accuracy of the current 1-bit CNNs is much worse compared to their…
In this paper, we study 1-bit convolutional neural networks (CNNs), of which both the weights and activations are binary. While efficient, the lacking of representational capability and the training difficulty impede 1-bit CNNs from…
Non-volatile memory (NVM) crossbars have been identified as a promising technology, for accelerating important machine learning operations, with matrix-vector multiplication being a key example. Binary neural networks (BNNs) are especially…
A key enabler of deploying convolutional neural networks on resource-constrained embedded systems is the binary neural network (BNN). BNNs save on memory and simplify computation by binarizing both features and weights. Unfortunately,…
Recent work has shown that fast, compact low-bitwidth neural networks can be surprisingly accurate. These networks use homogeneous binarization: all parameters in each layer or (more commonly) the whole model have the same low bitwidth…
This paper proposes an improved training algorithm for binary neural networks in which both weights and activations are binary numbers. A key but fairly overlooked feature of the current state-of-the-art method of XNOR-Net is the use of…
This paper investigates two prominent probabilistic neural modeling paradigms: Bayesian Neural Networks (BNNs) and Mixture Density Networks (MDNs) for uncertainty-aware nonlinear regression. While BNNs incorporate epistemic uncertainty by…
Deep neural networks have significantly improved performance on a range of tasks with the increasing demand for computational resources, leaving deployment on low-resource devices (with limited memory and battery power) infeasible. Binary…
Graph Neural Networks (GNNs) have emerged as a powerful and flexible framework for representation learning on irregular data. As they generalize the operations of classical CNNs on grids to arbitrary topologies, GNNs also bring much of the…
Low bit-width weights and activations are an effective way of combating the increasing need for both memory and compute power of Deep Neural Networks. In this work, we present a probabilistic training method for Neural Network with both…
Binary Convolutional Neural Networks (CNNs) can significantly reduce the number of arithmetic operations and the size of memory storage, which makes the deployment of CNNs on mobile or embedded systems more promising. However, the accuracy…
Ternary and binary neural networks enable multiplication-free computation and promise multiple orders of magnitude efficiency gains over full-precision networks if implemented on specialized hardware. However, since both the parameter and…
Binary neural networks (BNNs) have been widely adopted to reduce the computational cost and memory storage on edge-computing devices by using one-bit representation for activations and weights. However, as neural networks become…
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…
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…
The binary neural network, largely saving the storage and computation, serves as a promising technique for deploying deep models on resource-limited devices. However, the binarization inevitably causes severe information loss, and even…