Related papers: Binary Weight Multi-Bit Activation Quantization fo…

Computing-in-memory (CIM) architectures demonstrate superior performance over traditional architectures. To unleash the potential of CIM accelerators, many compilation methods have been proposed, focusing on application scheduling…

Convolutional neural network (CNN) has been widely used for vision-based tasks. Due to the high computational complexity and memory storage requirement, it is hard to directly deploy a full-precision CNN on embedded devices. The…

Bayesian Neural Networks (BNNs) can overcome the problem of overconfidence that plagues traditional frequentist deep neural networks, and are hence considered to be a key enabler for reliable AI systems. However, conventional hardware…

We investigate the compression of deep neural networks by quantizing their weights and activations into multiple binary bases, known as multi-bit networks (MBNs), which accelerate the inference and reduce the storage for the deployment on…

Loom (LM), a hardware inference accelerator for Convolutional Neural Networks (CNNs) is presented. In LM every bit of data precision that can be saved translates to proportional performance gains. Specifically, for convolutional layers LM's…

Binary quantization represents the most extreme form of compression, reducing weights to +/-1 for maximal memory and computational efficiency. While recent sparsity-aware binarization achieves sub-1-bit compression via weight pruning, it…

The Spiking Neural Network (SNN), a biologically inspired neural network infrastructure, has garnered significant attention recently. SNNs utilize binary spike activations for efficient information transmission, replacing multiplications…

Post-training, layer-wise quantization is preferable because it is free from retraining and is hardware-friendly. Nevertheless, accuracy degradation has occurred when a neural network model has a big difference of per-out-channel weight…

Deep neural networks (DNNs) can be made hardware-efficient by reducing the numerical precision of the weights and activations of the network and by improving the network's resilience to noise. However, this gain in efficiency often comes at…

Binary matrix-vector multiplication (BMVM) is a key operation in post-quantum cryptography schemes like the Classic McEliece cryptosystem. Conventional computing architectures incur significant energy efficiency loss due to data movement of…

Based on the assumption that there exists a neural network that efficiently represents a set of Boolean functions between all binary inputs and outputs, we propose a process for developing and deploying neural networks whose weight…

In recent years, hardware-accelerated neural networks have gained significant attention for edge computing applications. Among various hardware options, crossbar arrays, offer a promising avenue for efficient storage and manipulation of…

In recent years, Convolutional Neural Networks (CNNs) have become the standard class of deep neural network for image processing, classification and segmentation tasks. However, the large strides in accuracy obtained by CNNs have been…

There has been many papers in academic literature on quantizing weight tensors in deep learning models to reduce inference latency and memory footprint. TVM also has the ability to quantize weights and support low-bit computations. Although…

Model quantization is leveraged to reduce the memory consumption and the computation time of deep neural networks. This is achieved by representing weights and activations with a lower bit resolution when compared to their high precision…

Weight quantization is used to deploy high-performance deep learning models on resource-limited hardware, enabling the use of low-precision integers for storage and computation. Spiking neural networks (SNNs) share the goal of enhancing…

In this paper, we propose to employ a bank of modality-dedicated Convolutional Neural Networks (CNNs), fuse, train, and optimize them together for person classification tasks. A modality-dedicated CNN is used for each modality to extract…

Processing-in-memory (PIM), an increasingly studied neuromorphic hardware, promises orders of energy and throughput improvements for deep learning inference. Leveraging the massively parallel and efficient analog computing inside memories,…

We show that, during inference with Convolutional Neural Networks (CNNs), more than 2x to $8x ineffectual work can be exposed if instead of targeting those weights and activations that are zero, we target different combinations of value…

We present a novel sub-8-bit quantization-aware training (S8BQAT) scheme for 8-bit neural network accelerators. Our method is inspired from Lloyd-Max compression theory with practical adaptations for a feasible computational overhead during…