Publications associées à A Product Engine for Energy-Efficient Execution of Binary Neural Networks Using Resistive Memories

Publications associées (39)

OPTIMAL TRANSPORT-INSPIRED DEEP LEARNING FRAMEWORK FOR SLOW-DECAYING KOLMOGOROV \bfitn-WIDTH PROBLEMS: EXPLOITING SINKHORN LOSS AND WASSERSTEIN KERNEL

Reduced-order models (ROMs) are widely used in scientific computing to tackle high-dimensional systems. However, traditional ROM methods may only partially capture the intrinsic geometric characteristics of the data. These characteristics encompass the und ...

2025

High-dimensional learning of narrow neural networks

Hugo Chao Cui

Recent years have been marked with the fast-pace diversification and increasing ubiquity of machine learning (ML) applications. Yet, a firm theoretical understanding of the surprising efficiency of neural networks (NNs) to learn from high-dimensional data ...

2025

Gradient Approximation of Approximate Multipliers for High-Accuracy Deep Neural Network Retraining

Giovanni De Micheli, Chang Meng

Approximate multipliers (AppMults) are widely employed in deep neural network (DNN) accelerators to reduce the area, delay, and power consumption. However, the inaccuracies of AppMults degrade DNN accuracy, necessitating a retraining process to recover acc ...

Institute of Electrical and Electronics Engineers2025

Exploiting XAI Maps to Improve MS Lesion Segmentation and Detection in MRI

Meritxell Bach Cuadra

To date, several methods have been developed to explain deep learning algorithms for classification tasks. Recently, an adaptation of two of such methods has been proposed to generate instance-level explainable maps in a semantic segmentation scenario, suc ...

Springer2025

Exploring High-Performance and Energy-Efficient Architectures for Edge AI-Enabled Applications

Joshua Alexander Harrison Klein

The desire and ability to place AI-enabled applications on the edge has grown significantly in recent years. However, the compute-, area-, and power-constrained nature of edge devices are stressed by the needs of the AI-enabled applications, due to a gener ...

EPFL2024

EdgeAI-Aware Design of In-Memory Computing Architectures

Marco Antonio Rios

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 ...

EPFL2024

Improving Lipschitz-Constrained Neural Networks by Learning Activation Functions

Michaël Unser, Dimitris Perdios, Alexis Marie Frederic Goujon, Pakshal Narendra Bohra, Sebastian Jonas Neumayer, Stanislas Ducotterd

Lipschitz-constrained neural networks have several advantages over unconstrained ones and can be applied to a variety of problems, making them a topic of attention in the deep learning community. Unfortunately, it has been shown both theoretically and empi ...

2024

Random matrix methods for high-dimensional machine learning models

Antoine Philippe Michel Bodin

In the rapidly evolving landscape of machine learning research, neural networks stand out with their ever-expanding number of parameters and reliance on increasingly large datasets. The financial cost and computational resources required for the training p ...

EPFL2024

Predicting electronic screening for fast Koopmans spectral functional calculations

Nicola Marzari

Koopmans spectral functionals are a powerful extension of Kohn-Sham density-functional theory (DFT) that enables the prediction of spectral properties with state-of-the-art accuracy. The success of these functionals relies on capturing the effects of elect ...

2024

Secure Interface Design Leveraging Hardware/Software Support

Atri Bhattacharyya

Computer systems rely heavily on abstraction to manage the exponential growth of complexity across hardware and software. Due to practical considerations of compatibility between components of these complex systems across generations, developers have favou ...

EPFL2024

Wigner kernels: Body-ordered equivariant machine learning without a basis

Michele Ceriotti, Sergey Pozdnyakov, Filippo Bigi

Machine-learning models based on a point-cloud representation of a physical object are ubiquitous in scientific applications and particularly well-suited to the atomic-scale description of molecules and materials. Among the many different approaches that h ...

AIP Publishing2024

Coupling a recurrent neural network to SPAD TCSPC systems for real-time fluorescence lifetime imaging

Edoardo Charbon, Claudio Bruschini, Andrei Ardelean, Paul Mos, Yang Lin

Fluorescence lifetime imaging (FLI) has been receiving increased attention in recent years as a powerful diagnostic technique in biological and medical research. However, existing FLI systems often suffer from a tradeoff between processing speed, accuracy, ...

Nature Portfolio2024

Topics in statistical physics of high-dimensional machine learning

Hugo Chao Cui

In the past few years, Machine Learning (ML) techniques have ushered in a paradigm shift, allowing the harnessing of ever more abundant sources of data to automate complex tasks. The technical workhorse behind these important breakthroughs arguably lies in ...

EPFL2024

Intermediate Address Space: virtual memory optimization of heterogeneous architectures for cache-resident workloads

Qunyou Liu, David Atienza Alonso, Marina Zapater Sancho, Darong Huang, Luis Maria Costero Valero

The increasing demand for computing power and the emergence of heterogeneous computing architectures have driven the exploration of innovative techniques to address current limitations in both the compute and memory subsystems. One such solution is the use ...

2024

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Volkan Cevher, Grigorios Chrysos, Fanghui Liu

Despite the widespread empirical success of ResNet, the generalization properties of deep ResNet are rarely explored beyond the lazy training regime. In this work, we investigate scaled ResNet in the limit of infinitely deep and wide neural networks, of wh ...

2024

Safe Deep Neural Networks

Kyle Michael Matoba

The capabilities of deep learning systems have advanced much faster than our ability to understand them. Whilst the gains from deep neural networks (DNNs) are significant, they are accompanied by a growing risk and gravity of a bad outcome. This is troubli ...

EPFL2024

Optimizing Dynamic Aperture Studies with Active Learning

Tatiana Pieloni, Mike Seidel, Davide Di Croce, Ekaterina Krymova

Dynamic aperture is an important concept for the study of non-linear beam dynamics in circular accelerators. It describes the extent of the phase-space region where a particle's motion remains bounded over a given number of turns. Understanding the feature ...

Iop Publishing Ltd2024

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

Mattia Atzeni

The ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...

EPFL2024

Reduced Training Data for Laser Ultrasound Signal Interpretation by Neural Networks

Romain Christophe Rémy Fleury, Janez Rus

The performance of machine learning algorithms is conditioned by the availability of training datasets, which is especially true for the field of nondestructive evaluation. Here we propose one reconfigurable specimen instead of numerous reference specimens ...

2024

Error assessment of an adaptive finite elements-neural networks method for an elliptic parametric PDE

Maude Girardin, Marco Picasso, Alexandre Caboussat

We present a finite elements-neural network approach for the numerical approximation of parametric partial differential equations. The algorithm generates training data from finite element simulations, and uses a data -driven (supervised) feedforward neura ...

Elsevier Science Sa2024