Related papers: Factorized Blank Thresholding for Improved Runtime…

Contemporary Deep Neural Network (DNN) contains millions of synaptic connections with tens to hundreds of layers. The large computation and memory requirements pose a challenge to the hardware design. In this work, we leverage the intrinsic…

Deep neural network (DNN) based approaches hold significant potential for reinforcement learning (RL) and have already shown remarkable gains over state-of-art methods in a number of applications. The effectiveness of DNN methods can be…

Convolutional Neural Networks (CNNs) have become integral in safety-critical applications, thus raising concerns about their fault tolerance. Conventional hardware-dependent fault tolerance methods, such as Triple Modular Redundancy (TMR),…

The acoustic and linguistic features are important cues for the spoken language identification (LID) task. Recent advanced LID systems mainly use acoustic features that lack the usage of explicit linguistic feature encoding. In this paper,…

Sequence model based NLP applications can be large. Yet, many applications that benefit from them run on small devices with very limited compute and storage capabilities, while still having run-time constraints. As a result, there is a need…

The increasing computational demand of Convolutional Neural Networks (CNNs) necessitates energy-efficient acceleration strategies. Compute-in-Memory (CIM) architectures based on Resistive Random Access Memory (RRAM) offer a promising…

With the popularity of the deep neural network (DNN), hardware accelerators are demanded for real time execution. However, lengthy design process and fast evolving DNN models make hardware evaluation hard to meet the time to market need.…

Massive MIMO systems have the potential to significantly enhance spectral efficiency, yet their widespread integration is hindered by the high power consumption of the underlying computations. This paper explores the applicability and…

The Fast Fourier Transform (FFT) is the most efficiently known way to compute the Discrete Fourier Transform (DFT) of an arbitrary n-length signal, and has a computational complexity of O(n log n). If the DFT X of the signal x has only k…

Recurrent Neural Networks (RNNs) have been widely used in sequence analysis and modeling. However, when processing high-dimensional data, RNNs typically require very large model sizes, thereby bringing a series of deployment challenges.…

The computational complexity of neural networks for large scale or real-time applications necessitates hardware acceleration. Most approaches assume that the network architecture and parameters are unknown at design time, permitting usage…

Faster-than-Nyquist (FTN) signaling aims at improving the spectral efficiency of wireless communication systems by exceeding the boundaries set by the Nyquist-Shannon sampling theorem. 50 years after its first introduction in the scientific…

Inference efficiency is the predominant consideration in designing deep learning accelerators. Previous work mainly focuses on skipping zero values to deal with remarkable ineffectual computation, while zero bits in non-zero values, as…

Fully non-autoregressive neural machine translation (NAT) is proposed to simultaneously predict tokens with single forward of neural networks, which significantly reduces the inference latency at the expense of quality drop compared to the…

In this work, we demonstrate the offline FPGA realization of both recurrent and feedforward neural network (NN)-based equalizers for nonlinearity compensation in coherent optical transmission systems. First, we present a realization…

Popular solutions to Named Entity Recognition (NER) include conditional random fields, sequence-to-sequence models, or utilizing the question-answering framework. However, they are not suitable for nested and overlapping spans with large…

Spiking Neural Networks (SNN) are a class of bio-inspired neural networks that promise to bring low-power and low-latency inference to edge devices through asynchronous and sparse processing. However, being temporal models, SNNs depend…

We investigate pruning and quantization for deep neural networks. Our goal is to achieve extremely high sparsity for quantized networks to enable implementation on low cost and low power accelerator hardware. In a practical scenario, there…

Number Theoretic Transform (NTT) is an essential mathematical tool for computing polynomial multiplication in promising lattice-based cryptography. However, costly division operations and complex data dependencies make efficient and…

Spiking Neural Networks (SNNs) have gained significant attention as a potentially energy-efficient alternative for standard neural networks with their sparse binary activation. However, SNNs suffer from memory and computation overhead due…