Related papers: Analog Implementation of the Softmax Function
The transformer neural network architecture uses a form of attention in which the dot product of query and key is divided by the square root of the key dimension before applying softmax. This scaling of the dot product is designed to avoid…
An analog synapse circuit based on ferroelectric-metal field-effect transistors is proposed, that offers 6-bit weight precision. The circuit is comprised of volatile least significant bits (LSBs) used solely during training, and…
A switched-capacitor matrix multiplier is presented for approximate computing and machine learning applications. The multiply-and-accumulate operations perform discrete-time charge-domain signal processing using passive switches and 300 aF…
Always-on AI applications, from environmental sensors to biomedical implants, require ultra-low power consumption. Analog circuits offer a path to sub-microwatt inference, yet existing analog implementations are limited to feedforward…
Nowadays artificial neural network models achieve remarkable results in many disciplines. Functions mapping the representation provided by the model to the probability distribution are the inseparable aspect of deep learning solutions.…
Recently, in-memory analog matrix computing (AMC) with nonvolatile resistive memory has been developed for solving matrix problems in one step, e.g., matrix inversion of solving linear systems. However, the analog nature sets up a barrier…
Analog Content Addressable Memories (aCAMs) have proven useful for associative in-memory computing applications like Decision Trees, Finite State Machines, and Hyper-dimensional Computing. While non-volatile implementations using FeFETs and…
Deploying mixed-precision neural networks on edge devices is friendly to hardware resources and power consumption. To support fully mixed-precision neural network inference, it is necessary to design flexible hardware accelerators for…
The softmax content-based attention mechanism has proven to be very beneficial in many applications of recurrent neural networks. Nevertheless it suffers from two major computational limitations. First, its computations for an attention…
Memory allocation, though constituting only a small portion of the executed code, can have a "butterfly effect" on overall program performance, leading to significant and far-reaching impacts. Despite accounting for just approximately 5% of…
Soft robots are powerful tools for manipulating delicate objects, yet their adoption is hindered by two gaps: the lack of integrated tactile sensing and sensor signal distortion caused by actuator deformations. This paper addresses these…
We investigate time-adaptive Magnus-type integrators for the numerical approximation of a Mott transistor. The rapidly attenuating electromagnetic field calls for adaptive choice of the time steps. As a basis for step selection,…
In classification tasks, softmax functions are ubiquitously used as output activations to produce predictive probabilities. Such outputs only capture aleatoric uncertainty. To capture epistemic uncertainty, approximate Gaussian inference…
Transformers have improved drastically the performance of natural language processing (NLP) and computer vision applications. The computation of transformers involves matrix multiplications and non-linear activation functions such as…
CMOS-transistors circuits have been used as a conventional approach for designing an analog multiplier in modern era of industrial electronics. However, previous studies have shown, that based on the working region of transistors, such as…
The rapid scaling of language models is motivating research using low-bitwidth quantization. In this work, we propose a novel binarization technique for Transformers applied to machine translation (BMT), the first of its kind. We identify…
In this work, we optimize speculative sampling for parallel hardware accelerators to improve sampling speed. We notice that substantial portions of the intermediate matrices necessary for speculative sampling can be computed concurrently.…
The softmax representation of probabilities for categorical variables plays a prominent role in modern machine learning with numerous applications in areas such as large scale classification, neural language modeling and recommendation…
This thesis develops signal-processing algorithms and implementation schemes under constraints of minimal parallelism and memory space, with the goal of improving energy efficiency of low-power computing hardware. We propose (i) a…
Bipolar junction transistors (BJTs) have been at the core of linear electronics from its beginnings. Although their properties can be well represented transport model equations, design and analysis approaches have, to a good extent, been…