Related papers: Assessing the Performance of Analog Training for T…

Spiking neural networks (SNNs) operating with asynchronous discrete events show higher energy efficiency with sparse computation. A popular approach for implementing deep SNNs is ANN-SNN conversion combining both efficient training of ANNs…

Operator learning, which aims to approximate maps between infinite-dimensional function spaces, is an important area in scientific machine learning with applications across various physical domains. Here we introduce the Continuous Vision…

The growing demand for edge computing and AI drives research into analog in-memory computing using memristors, which overcome data movement bottlenecks by computing directly within memory. However, device failures and variations critically…

The ubiquity of vision transformers (ViTs) for various edge applications, including personalized learning, has created the demand for on-device fine-tuning. However, training with the limited memory and computation power of edge devices…

Analog In-Memory Compute (AIMC) can improve the energy efficiency of Deep Learning by orders of magnitude. Yet analog-domain device and circuit non-idealities -- within the analog ``Tiles'' performing Matrix-Vector Multiply (MVM) operations…

Always-on TinyML perception tasks in IoT applications require very high energy efficiency. Analog compute-in-memory (CiM) using non-volatile memory (NVM) promises high efficiency and also provides self-contained on-chip model storage.…

Self-attention and transformers have been widely used in deep learning. Recent efforts have been devoted to incorporating transformer blocks into different neural architectures, including those with convolutions, leading to various visual…

A churn prediction system guides telecom service providers to reduce revenue loss. However, the development of a churn prediction system for a telecom industry is a challenging task, mainly due to the large size of the data, high…

In this work, we address the question of the adaptability of artificial neural networks (NNs) used for impairments mitigation in optical transmission systems. We demonstrate that by using well-developed techniques based on the concept of…

Meta-learning has been proposed as a framework to address the challenging few-shot learning setting. The key idea is to leverage a large number of similar few-shot tasks in order to learn how to adapt a base-learner to a new task for which…

Fine-grained classification is a challenging task that involves identifying subtle differences between objects within the same category. This task is particularly challenging in scenarios where data is scarce. Visual transformers (ViT) have…

Deep Learning (DL) algorithms are the central focus of modern machine learning systems. As data volumes keep growing, it has become customary to train large neural networks with hundreds of millions of parameters to maintain enough capacity…

With the development of new sensors and monitoring devices, more sources of data become available to be used as inputs for machine learning models. These can on the one hand help to improve the accuracy of a model. On the other hand,…

Analog/mixed-signal circuit design encounters significant challenges due to performance degradation from process, voltage, and temperature (PVT) variations. To achieve commercial-grade reliability, iterative manual design revisions and…

Transfer learning (TL) techniques, which leverage prior knowledge gained from data with different distributions to achieve higher performance and reduced training time, are often used in computer vision (CV) and natural language processing…

Imaging in clinical routine is subject to changing scanner protocols, hardware, or policies in a typically heterogeneous set of acquisition hardware. Accuracy and reliability of deep learning models suffer from those changes as data and…

Spiking neural networks (SNNs) are shown to be more biologically plausible and energy efficient over their predecessors. However, there is a lack of an efficient and generalized training method for deep SNNs, especially for deployment on…

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…

Transferring knowledge from prior source tasks in solving a new target task can be useful in several learning applications. The application of transfer poses two serious challenges which have not been adequately addressed. First, the agent…

Incorporating self-supervised learning (SSL) before standard supervised learning (SL) has become a widely used strategy to enhance model performance, particularly in data-limited scenarios. However, this approach introduces a trade-off…