Lupulus: A Flexible Hardware Accelerator For Neural Networks

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.

Transformers trained on natural language data have been shown to exhibit hierarchical generalization without explicitly encoding any structural bias. In this work, we investigate sources of inductive bias in transformer models and their training that could ...

A search is presented for an extended Higgs sector with two new particles, (Formula presented) and (Formula presented), in the process (Formula presented). Novel neural networks classify events with diphotons that are merged and determine the diphoton mass ...

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 ...

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 ...

Enterprises collect data in large volumes and leverage them to drive numerous concurrent decisions and business processes. Their teams deploy multiple applications that often operate concurrently on the same data and infrastructure but have widely differen ...

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 ...

Much attention has been paid to dynamical simulation and quantum machine learning (QML) independently as applications for quantum advantage, while the possibility of using QML to enhance dynamical simulations has not been thoroughly investigated. Here we d ...

The construction industry plays a major role in the high levels of greenhouse gas emissions, resource consumption, and waste generation observed nowadays. Key to the circular economy, structural component reuse arises as a promising solution to divert cons ...

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 ...

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 ...

Electrical stimulation of the visual nervous system could improve the quality of life of patients affected by acquired blindness by restoring some visual sensations, but requires careful optimization of stimulation parameters to produce useful perceptions. ...

Throughout history, the pace of knowledge and information sharing has evolved into an unthinkable speed and media. At the end of the XVII century, in Europe, the ideas that would shape the "Age of Enlightenment" were slowly being developed in coffeehouses, ...

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 ...

In this PhD manuscript, we explore optimisation phenomena which occur in complex neural networks through the lens of

2

-layer diagonal linear networks. This rudimentary architecture, which consists of a two layer feedforward linear network with a diagonal ...

The upcoming Square Kilometre Array Observatory will produce images of neutral hydrogen distribution during the epoch of reionization by observing the corresponding 21-cm signal. However, the 21-cm signal will be subject to instrumental limitations such as ...

In droplet microfluidic devices with suction-based flow control, the microchannel geometry and suction pressure at the outlet govern the dynamic properties of the two phases that influence the droplet generation. Therefore, it is critical to understand the ...

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 ...

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 ...

Here we provide the neural data, activation and predictions for the best models and result dataframes of our article "Task-driven neural network models predict neural dynamics of proprioception". It contains the behavioral and neural experimental data (cu ...

This paper presents a comparison of machine learning (ML) methods used for three-dimensional localization of partial discharges (PD) in a power transformer tank. The study examines ML and deep learning (DL) methods, ranging from support vector machines (SV ...

Lupulus: A Flexible Hardware Accelerator For Neural Networks

Chat with Graph Search

Learning Syntax Without Planting Trees: Understanding Hierarchical Generalization in Transformers

Search for New Resonances Decaying to Pairs of Merged Diphotons in Proton-Proton Collisions at (Formula presented)

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

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

Oligolithic Cross-task Optimizations across Isolated Workloads

Topics in statistical physics of high-dimensional machine learning

Dynamical simulation via quantum machine learning with provable generalization

RE:SLAB — a load bearing system for open-ended component reuse in building structures

Reduced Training Data for Laser Ultrasound Signal Interpretation by Neural Networks

Optimizing Dynamic Aperture Studies with Active Learning

Decoding electroencephalographic responses to visual stimuli compatible with electrical stimulation

Machine Learning for Modeling Stock Returns

Random matrix methods for high-dimensional machine learning models

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Deep learning approach for identification of H II regions during reionization in 21-cm observations - II. Foreground contamination

Modified capillary number to standardize droplet generation in suction-driven microfluidics

Safe Deep Neural Networks

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Task-driven neural network models predict neural dynamics of proprioception: Experimental data, activations and predictions of neural network models

Partial discharge localization in power transformer tanks using machine learning methods