Related papers: Fault Tolerant Reconfigurable ML Multiprocessor

The exponential growth in LLM scales, with parameters soaring from billions to trillions, has necessitated distributed pretraining across large clusters comprising thousands to tens of thousands of devices. While hybrid parallelization…

In this work, we consider the adaptive nonlinear control problem for strict feedback nonlinear systems, where the functions that determine the dynamics of the system are completely unknown. We assume that certain upper bounds for the…

Over the past decades, researchers have primarily focused on improving the generalization abilities of models, with limited attention given to regulating such generalization. However, the ability of models to generalize to unintended data…

This paper examines the problem of introducing advanced forms of fault-tolerance via reconfiguration into safety-critical avionic systems. This is required to enable increased availability after fault occurrence in distributed integrated…

Multimodal deep learning systems are deployed in dynamic scenarios due to the robustness afforded by multiple sensing modalities. Nevertheless, they struggle with varying compute resource availability (due to multi-tenancy, device…

With the rapid advancements of deep learning in the past decade, it can be foreseen that deep learning will be continuously deployed in more and more safety-critical applications such as autonomous driving and robotics. In this context,…

Neural networks are known to be vulnerable to adversarial attacks, which are small, imperceptible perturbations that can significantly alter the network's output. Conversely, there may exist large, meaningful perturbations that do not…

Fine-tuning pre-trained Neural Machine Translation (NMT) models is the dominant approach for adapting to new languages and domains. However, fine-tuning requires adapting and maintaining a separate model for each target task. We propose a…

We propose using reinforcement learning to address the challenges of discovering microarchitectural vulnerabilities, such as Spectre and Meltdown, which exploit subtle interactions in modern processors. Traditional methods like random…

This paper proposes an adaptive tracking control with prescribed performance function for distributive cooperative control of highly nonlinear multi-agent systems. The use of such approach confines the tracking error within a large…

In this short review, I draw attention to new developments in the theory of fault tolerance in quantum computation that may give concrete direction to future work in the development of superconducting qubit systems. The basics of quantum…

Fault-aware retraining has emerged as a prominent technique for mitigating permanent faults in Deep Neural Network (DNN) hardware accelerators. However, retraining leads to huge overheads, specifically when used for fine-tuning large DNNs…

Can we take a recurrent neural network (RNN) trained to translate between languages and augment it to support a new natural language without retraining the model from scratch? Can we fix the faulty behavior of the RNN by replacing portions…

Convolutional neural networks (CNNs) are becoming very successful and popular for a variety of applications. The Loki many-core processor architecture is very promising for achieving specialised hardware performance and efficiency while…

Evolvable hardware combines the powerful search capability of evolutionary algorithms with the flexibility of reprogrammable devices, thereby providing a natural framework for reconfiguration. This framework has generated an interest in…

Ternary large language models (LLMs), which utilize ternary precision weights and 8-bit activations, have demonstrated competitive performance while significantly reducing the high computational and memory requirements of full-precision…

The deployment of deep neural networks (DNNs) in safety-critical edge environments necessitates robustness against hardware-induced bit-flip errors. While empirical studies indicate that reducing numerical precision can improve fault…

In this paper, we present a new MTL framework that searches for structures optimized for multiple tasks with diverse graph topologies and shares features among tasks. We design a restricted DAG-based central network with read-in/read-out…

In this paper, we propose a novel cross-platform fault-tolerant surfacing controller for underwater robots, based on reinforcement learning (RL). Unlike conventional approaches, which require explicit identification of malfunctioning…

This paper introduces a novel approach to Dynamic Artificial Neural Networks (D-ANNs) for multi-task demand forecasting called Neuroplastic Multi-Task Network (NMT-Net). Unlike conventional methods focusing on inference-time dynamics or…