Related papers: Learning Task-Based Trainable Neuromorphic ADCs vi…
We present a novel approach to knowledge transfer in model-based reinforcement learning, addressing the critical challenge of deploying large world models in resource-constrained environments. Our method efficiently distills a high-capacity…
One of the long-standing challenges in Artificial Intelligence for learning goal-directed behavior is to build a single agent which can solve multiple tasks. Recent progress in multi-task learning for goal-directed sequential problems has…
Efficient operation of intelligent machines in the real world requires methods that allow them to understand and predict the uncertainties presented by the unstructured environments with good accuracy, scalability and generalization,…
Artificial intelligence is widely used in everyday life. However, an insufficient computing efficiency due to the so-called von Neumann bottleneck cannot satisfy the demand for real-time processing of rapidly growing data. Memristive…
Analog in-memory computing (AIMC) is an energy-efficient alternative to digital architectures for accelerating machine learning and signal processing workloads. However, its energy efficiency is limited by the high energy cost of the column…
Central to the development of universal learning systems is the ability to solve multiple tasks without retraining from scratch when new data arrives. This is crucial because each task requires significant training time. Addressing the…
Deep 'Analog Artificial Neural Networks' (ANNs) perform complex classification problems with remarkably high accuracy. However, they rely on humongous amount of power to perform the calculations, veiling the accuracy benefits. The…
The massive use of artificial neural networks (ANNs), increasingly popular in many areas of scientific computing, rapidly increases the energy consumption of modern high-performance computing systems. An appealing and possibly more…
Nanoscale resistive switching devices (memristive devices or memristors) have been studied for a number of applications ranging from non-volatile memory, logic to neuromorphic systems. However a major challenge is to address the potentially…
Knowing how to reliably use memristors as information storage devices is crucial not only to their role as emerging memories, but also for their application in neural network acceleration and as components of novel neuromorphic systems. In…
Supervised machine learning-based medical image computing applications necessitate expert label curation, while unlabelled image data might be relatively abundant. Active learning methods aim to prioritise a subset of available image data…
In recent years, Compute-in-memory (CiM) architectures have emerged as a promising solution for deep neural network (NN) accelerators. Multiply-accumulate~(MAC) is considered a {\textit de facto} unit operation in NNs. By leveraging the…
Multiple-input multiple-output (MIMO) wireless systems conventionally use high-resolution analog-to-digital converters (ADCs) at the receiver side to faithfully digitize received signals prior to digital signal processing. However, the…
Memristors, initially introduced in the 1970s, have received increased attention upon successful synthesis in 2008. Considerable work has been done on modeling and applications in specific areas, however, very little is known on the…
Memristive associative learning has gained significant attention for its ability to mimic fundamental biological learning mechanisms while maintaining system simplicity. In this work, we introduce a high-order memristive associative…
Multi-task learning (MTL) models have demonstrated impressive results in computer vision, natural language processing, and recommender systems. Even though many approaches have been proposed, how well these approaches balance different…
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…
Autonomous driving systems rely on panoptic perception to jointly handle object detection, drivable area segmentation, and lane line segmentation. Although multi-task learning is an effective way to integrate these tasks, its increasing…
Recording reliably extracellular neural activities isan essential prerequisite for the development of bioelectronicsand neuroprosthetic applications. Recently, a fully differential,2-stage, integrating pre-amplifier was proposed for…
Autonomous AI agents operating in dynamic environments face a persistent challenge: acquiring new capabilities without erasing prior knowledge. We present Adaptive Memory Crystallization (AMC), a memory architecture for progressive…