Related papers: A 14uJ/Decision Keyword Spotting Accelerator with …

Analog-Based In-Memory Computing (AIMC) inference accelerators can be used to efficiently execute Deep Neural Network (DNN) inference workloads. However, to mitigate accuracy losses, due to circuit and device non-idealities, Hardware-Aware…

The Tsetlin Machine (TM) has recently attracted attention as a low-power alternative to neural networks due to its simple and interpretable inference mechanisms. However, its performance on speech-related tasks remains limited. This paper…

Transformers have become the backbone of neural network architecture for most machine learning applications. Their widespread use has resulted in multiple efforts on accelerating attention, the basic building block of transformers. This…

Large Language Models (LLMs) are scaling rapidly, creating significant challenges for collaborative server client distributed training, particularly in terms of communication efficiency and computational overheads. To address these…

The goal of this work is to detect new spoken terms defined by users. While most previous works address Keyword Spotting (KWS) as a closed-set classification problem, this limits their transferability to unseen terms. The ability to define…

Large language models (LLMs) are becoming increasingly capable at small parameter scales. At the same time, conventional cloud-centric deployment introduces challenges around data privacy, latency, and cost that are acute in operational…

Content Addressable Memories (CAMs) are considered a key-enabler for in-memory computing (IMC). IMC shows order of magnitude improvement in energy efficiency and throughput compared to traditional computing techniques. Recently, analog CAMs…

Mixed-signal hardware accelerators for deep learning achieve orders of magnitude better power efficiency than their digital counterparts. In the ultra-low power consumption regime, limited signal precision inherent to analog computation…

Analog in-memory computing (AIMC) performs computation directly within resistive crossbar arrays, offering an energy-efficient platform to scale large vision and language models. However, non-ideal analog device properties make the training…

This paper explores the adaptation of Transformerbased models for edge devices through the quantisation and hardware acceleration of the ARM Keyword Transformer (KWT) model on a RISC-V platform. The model was targeted to run on 64kB RAM in…

This paper introduces EdgeProfiler, a fast profiling framework designed for evaluating lightweight Large Language Models (LLMs) on edge systems. While LLMs offer remarkable capabilities in natural language understanding and generation,…

Using Large Language Models (LLMs) in real-world applications presents significant challenges, particularly in balancing computational efficiency with model performance. Optimizing acceleration after fine-tuning and during inference is…

Scaling to larger systems, with current levels of reliability, requires cost-effective methods to mitigate hardware failures. One of the main causes of hardware failure is an uncorrected error in memory, which terminates the current job and…

User-defined keyword spotting (KWS) is crucial for personalized voice interaction, yet existing methods face several challenges: (1) insufficient discriminability among confusable words, (2) performance inconsistency across speakers with…

The attention mechanism is a key computing kernel of Transformers, calculating pairwise correlations across the entire input sequence. The computing complexity and frequent memory access in computing self-attention put a huge burden on the…

Low bit-width Quantized Neural Networks (QNNs) enable deployment of complex machine learning models on constrained devices such as microcontrollers (MCUs) by reducing their memory footprint. Fine-grained asymmetric quantization (i.e.,…

Resistive In-Memory Computing (RIMC) offers ultra-efficient computation for edge AI but faces accuracy degradation due to RRAM conductance drift over time. Traditional retraining methods are limited by RRAM's high energy consumption, write…

With the surging popularity of edge computing, the need to efficiently perform neural network inference on battery-constrained IoT devices has greatly increased. While algorithmic developments enable neural networks to solve increasingly…

Bayesian Neural Networks (BNNs) provide superior estimates of uncertainty by generating an ensemble of predictive distributions. However, inference via ensembling is resource-intensive, requiring additional entropy sources to generate…

Catastrophic forgetting is a thorny challenge when updating keyword spotting (KWS) models after deployment. To tackle such challenges, we propose a progressive continual learning strategy for small-footprint spoken keyword spotting…