Related papers: Reliability-Aware Quantization for Anti-Aging NPUs

This paper presents a compression framework for Reservoir Computing that enables systematic design-space exploration of trade-offs among quantization levels, pruning rates, model accuracy, and hardware efficiency. The proposed approach…

Deep Neural Networks are highly over-parameterized and the size of the neural networks can be reduced significantly after training without any decrease in performance. One can clearly see this phenomenon in a wide range of architectures…

The effects of quantization and coding on the estimation quality of Gauss-Markov processes are considered, with a special attention to the Ornstein-Uhlenbeck process. Samples are acquired from the process, quantized, and then encoded for…

This paper reports the impacts of temperature variation on the inference accuracy of pre-trained all-ferroelectric FinFET deep neural networks, along with plausible design techniques to abate these impacts. We adopted a pre-trained…

Access to quantum computing is steadily increasing each year as the speed advantage of quantum computers solidifies with the growing number of usable qubits. However, the inherent noise encountered when running these systems can lead to…

Quantized neural networks (QNNs) have received increasing attention in resource-constrained scenarios due to their exceptional generalizability. However, their robustness against realistic black-box adversarial attacks has not been…

We present a scheme to neutralize the dephasing effect induced by classical noise on a qubit. The scheme builds upon the key idea that this kind of noise can be recorded by a classical device during the qubit evolution, and that its effect…

Diffusion transformers have demonstrated remarkable capabilities in generating videos. However, their practical deployment is severely constrained by high memory usage and computational cost. Post-Training Quantization provides a practical…

Deep Neural Networks reached state-of-the-art performance across numerous domains, but this progress has come at the cost of increasingly large and over-parameterized models, posing serious challenges for deployment on resource-constrained…

Developing methods to accurately characterize and mitigate the impact of noise is crucial for enhancing the fidelity of quantum simulations on Noisy Intermediate-Scale Quantum (NISQ) devices. In this work, we present a circuit…

The deployment of machine learning (ML) models on microcontrollers (MCUs) is constrained by strict energy, latency, and memory requirements, particularly in battery-operated and real-time edge devices. While software-level optimizations…

This whitepaper proposes the design and adoption of a new generation of Tensor Processing Unit which has the performance of Google's TPU, yet performs operations on wide precision data. The new generation TPU is made possible by…

Quantum noise limits the use of quantum memory in high energy physics simulations. In particular, it breaks the gauge symmetry of stored quantum states. We examine this effect for abelian and nonabelian theories and demonstrate that…

Deploying machine learning-based intrusion detection systems (IDSs) on hardware devices is challenging due to their limited computational resources, power consumption, and network connectivity. Hence, there is a significant need for robust,…

Training neural networks requires significant computational resources and energy. Methods like mixed-precision and quantization-aware training reduce bit usage, yet they still depend heavily on computationally expensive gradient-based…

The assessment of noise margins and the related probability of failure in digital cells has growingly become essential, as nano-scale CMOS and FinFET technologies are confronting reliability issues caused by aging mechanisms, such as NBTI,…

Transformer life assessment and failure diagnostics have always been important problems for electric utility companies. Ambient temperature and load profile are the main factors which affect aging of the transformer insulation, and…

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…

We propose a network architecture capable of reliably estimating uncertainty of regression based predictions without sacrificing accuracy. The current state-of-the-art uncertainty algorithms either fall short of achieving prediction…

The memorization problem is well-known in the field of computer vision. Liu et al. propose a technique called Early-Learning Regularization, which improves accuracy on the CIFAR datasets when label noise is present. This project replicates…