Related papers: Characterization and Mitigation of ADC Noise by Re…

Our recent work (Ayral et al., 2020 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)) showed the first implementation of the Quantum Divide and Compute (QDC) method, which allows to break quantum circuits into smaller fragments with…

Modern edge AI workloads demand maximum energy efficiency, motivating the pursuit of analog Compute-in-Memory (CIM) architectures. Simultaneously, the popularity of Large-Language-Models (LLMs) drives the adoption of low-bit floating-point…

Deep learning training involves a large number of operations, which are dominated by high dimensionality Matrix-Vector Multiplies (MVMs). This has motivated hardware accelerators to enhance compute efficiency, but where data movement and…

Retrieval-Augmented Language Models (RALMs) have demonstrated significant potential in knowledge-intensive tasks; however, they remain vulnerable to performance degradation when presented with irrelevant or noisy retrieved contexts.…

We study and analyze the fundamental aspects of noise propagation in recurrent as well as deep, multi-layer networks. The main focus of our study are neural networks in analogue hardware, yet the methodology provides insight for networks in…

Computing-in-Memory (CiM) architectures based on emerging non-volatile memory (NVM) devices have demonstrated great potential for deep neural network (DNN) acceleration thanks to their high energy efficiency. However, NVM devices suffer…

Compute-in-memory (CIM) is an efficient method for implementing deep neural networks (DNNs) but suffers from substantial overhead from analog-to-digital converters (ADCs), especially as ADC precision increases. Low-precision ADCs can reduce…

Recently, RRAM-based Binary Neural Network (BNN) hardware has been gaining interests as it requires 1-bit sense-amp only and eliminates the need for high-resolution ADC and DAC. However, RRAM-based BNN hardware still requires…

Non-volatile memory arrays can deploy pre-trained neural network models for edge inference. However, these systems are affected by device-level noise and retention issues. Here, we examine damage caused by these effects, introduce a…

Binary neural networks (BNNs) that use 1-bit weights and activations have garnered interest as extreme quantization provides low power dissipation. By implementing BNNs as computing-in-memory (CIM), which computes multiplication and…

Processing-in-memory (PIM) architectures have demonstrated great potential in accelerating numerous deep learning tasks. Particularly, resistive random-access memory (RRAM) devices provide a promising hardware substrate to build PIM…

The human brain simultaneously optimizes synaptic weights and topology by growing, pruning, and strengthening synapses while performing all computation entirely in memory. In contrast, modern artificial-intelligence systems separate weight…

The emergence of resistive non-volatile memories opens the way to highly energy-efficient computation near- or in-memory. However, this type of computation is not compatible with conventional ECC, and has to deal with device unreliability.…

Performing data-intensive tasks in the von Neumann architecture is challenging to achieve both high performance and power efficiency due to the memory wall bottleneck. Computing-in-memory (CiM) is a promising mitigation approach by enabling…

In this paper, we propose a framework to enhance the robustness of the neural models by mitigating the effects of process-induced and aging-related variations of analog computing components on the accuracy of the analog neural networks. We…

The interest in analog computation has grown tremendously in recent years due to its fast computation speed and excellent energy efficiency, which is very important for edge and IoT devices in the sub-watt power envelope for deep learning…

Edge computing is a promising solution for handling high-dimensional, multispectral analog data from sensors and IoT devices for applications such as autonomous drones. However, edge devices' limited storage and computing resources make it…

In cloud and edge computing models, it is important that compute devices at the edge be as power efficient as possible. Long short-term memory (LSTM) neural networks have been widely used for natural language processing, time series…

Resistive random-access memory (RRAM) provides an excellent platform for analog matrix computing (AMC), enabling both matrix-vector multiplication (MVM) and the solution of matrix equations through open-loop and closed-loop circuit…

Stability of ultra-low-voltage SRAM bitcells in retention mode is threatened by two types of uncertainty: process variability and intrinsic noise. While variability dominates the failure probability, noise-induced bit flips in weakened…