A Hybrid Cache HW/SW Stack for Optimizing Neural Network Runtime, Power and Endurance

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

This paper presents a theoretical analysis of linear interpolation as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss lan ...

Driven by the demand for real-time processing and the need to minimize latency in AI algorithms, edge computing has experienced remarkable progress. Decision-making AI applications stand out for their heavy reliance on data-centric operations, predominantl ...

This paper proposes a novel approach to improve the performance of distributed nonlinear control systems while preserving stability by leveraging Deep Neural Networks (DNNs). We build upon the Neural System Level Synthesis (Neur-SLS) framework and introduc ...

Analytical workloads are evolving as the number of users surges and applications that submit queries in batches become popular. However, traditional analytical databases that optimize-then-execute each query individually struggle to provide timely response ...

Ultrafast ultrasound imaging achieves high frame rates but results in lower image quality compared to focused acquisitions. Convolutional neural networks (CNNs) have emerged as effective tools for reducing diffraction artifacts and enhancing the quality of ...

Mapping behavioural actions to neural activity is a fundamental goal of neuroscience. As our ability to record large neural and behavioural data increases, there is growing interest in modelling neural dynamics during adaptive behaviours to probe neural re ...

Deep neural networks may easily memorize noisy labels present in real-world data, which degrades their ability to generalize. It is therefore important to track and evaluate the robustness of models against noisy label memorization. We propose a metric, ca ...

In this manuscript, we investigate the problem of how two-layer neural networks learn features from data, and improve over the kernel regime, after being trained with a single gradient descent step. Leveraging the insight from (Ba et al., 2022), we model t ...

In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...

Machine learning and data processing algorithms have been thriving in finding ways of processing and classifying information by exploiting the hidden trends of large datasets. Although these emerging computational methods have become successful in today's ...

Machine learning has transformed many fields and has recently found applications in chemistry and materials science. The small datasets commonly found in chemistry sparked the development of sophisticated machine learning approaches that incorporate chemic ...

The way biological brains carry out advanced yet extremely energy efficient signal processing remains both fascinating and unintelligible. It is known however that at least some areas of the brain perform fast and low-cost processing relying only on a smal ...

Numerical simulations have become an indispensable tool in astrophysics and cosmology. The constant need for higher accuracy, higher resolutions, and models of ever-increasing sophistication and complexity drives the development of modern tools which targe ...

A frequency scaling governor is critical for the performance management of cloud servers, as it enhances energy efficiency and helps to control operational temperatures, thereby ensuring system reliability. However, our in-depth analysis of the application ...

In the past decade, computing systems have significantly increased in complexity and power consumption. Nowadays, heterogeneous multi-processor systems-on-chip (MPSoCs) integrate many computing cores. Heterogeneous MPSoCs often comprise general-purpose pro ...

Despite their incredible performance, it is well reported that deep neural networks tend to be overoptimistic about their prediction confidence. Finding effective and efficient calibration methods for neural networks is therefore an important endeavour tow ...

A Hybrid Cache HW/SW Stack for Optimizing Neural Network Runtime, Power and Endurance

Chat with Graph Search

Stable Nonconvex-Nonconcave Training via Linear Interpolation

EdgeAI-Aware Design of In-Memory Computing Architectures

Optimal distributed control with stability guarantees by training a network of neural closed-loop maps

Efficient Concurrent Analytical Query Processing using Data and Workload-conscious Sharing

Enhancement of Ultrafast Ultrasound Images: A Performance Comparison Between CNN Trained with RF or IQ Images

Learnable latent embeddings for joint behavioural and neural analysis

Leveraging Unlabeled Data to Track Memorization

Asymptotics of feature learning in two-layer networks after one gradient-step

Understanding generalization and robustness in modern deep learning

2D Nanosystems: Applications of 2D Semiconductors for In-Memory Computing

Leveraging large language models for predictive chemistry

Supervised learning and inference of spiking neural networks with temporal coding

GEAR-RT: Towards Exa-Scale Moment Based Radiative Transfer For Cosmological Simulations Using Task-Based Parallelism And Dynamic Sub-Cycling with SWIFT

Is the powersave governor really saving power?

Cross-layer Exploration of 2.5D Energy-Efficient Heterogeneous Chiplets Integration: From System Simulation to Open Hardware

Expectation consistency for calibration of neural networks