Large-scale neural networks implemented with non-volatile memory as the synaptic weight element: impact of conductance response

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

Accurately estimating model performance poses a significant challenge, particularly in scenarios where the source and target domains follow different data distributions. Most existing performance prediction methods heavily rely on the source data in their ...

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 ...

Orthogonal frequency-division multiplexing (OFDM) is widely used to mitigate inter-symbol interference (ISI) from multipath fading. However, the open nature of wireless OFDM systems makes them vulnerable to jamming attacks. In this context, pilot jamming i ...

Vision Transformers (ViTs) demonstrate remarkable performance in image classification through visual-token interaction learning, particularly when equipped with local information via region attention or convolutions. Although such architectures improve the ...

As large, data-driven artificial intelligence models become ubiquitous, guaranteeing high data quality is imperative for constructing models. Crowdsourcing, community sensing, and data filtering have long been the standard approaches to guaranteeing or imp ...

In the past decades, a significant increase of the transistor density on a chip has led to exponential growth in computational power driven by Moore's law. To overcome the bottleneck of traditional von-Neumann architecture in computational efficiency, effo ...

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 ...

In this thesis, we conduct a comprehensive investigation into structural instabilities of both elastic and magneto-elastic beams and shells, resulting in a creative proposal to design a programmable braille reader. Methodologically, we combine numerical si ...

Objective: Brain-body interfaces (BBIs) have emerged as a very promising solution for restoring voluntary hand control in people with upper-limb paralysis. The BBI module decoding motor commands from brain signals should provide the user with intuitive, ac ...

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 ...

Atomistic simulations performed with a family of model potential with tunable hardness have proven to be a great tool for advancing the understanding of wear processes at the asperity level. They have been instrumental in finding a critical length scale, w ...

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 ...

Conventional lasers typically support a well‐defined comb of modes. Coupling many resonators together to form larger complex cavities enables the design of the spatial and spectral distribution of modes, for sensitive and controllable on‐chip light sources ...

Modern hardware is increasingly complex, requiring increasing effort to understand in order to carefully engineer systems for optimal performance and effective utilization. Moreover, established design principles and assumptions are not portable to modern ...

We consider the problem of learning a target function corresponding to a deep, extensive-width, non-linear neural network with random Gaussian weights. We consider the asymptotic limit where the number of samples, the input dimension and the network width ...

Accessing input data is a critical operation in data analytics: i) slow data access significantly degrades performance, and ii) storing everything in the fastest medium, i.e., memory, incurs high operational and hardware costs. Further, while GPUs offer in ...

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 ...

Physics-informed machine learning (PIML) is a set of methods and tools that systematically integrate machine learning (ML) algorithms with physical constraints and abstract mathematical models developed in scientific and engineering domains. As opposed to ...

Laser Powder Bed Fusion (LPBF) is an Additive Manufacturing (AM) process consolidating parts layer by layer, from a metallic powder bed. It allows no limitation in terms of geometry and is therefore of particular interest to various industries. Metallic LP ...

Large-scale neural networks implemented with non-volatile memory as the synaptic weight element: impact of conductance response

Chattez avec Graph Search

Source-Free Domain-Invariant Performance Prediction

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Adversarial Training for Jamming-Robust Channel Estimation in OFDM Systems

AdaNCA: Neural Cellular Automata as Adaptors for More Robust Vision Transformer

Extensions of Peer Prediction Incentive Mechanisms

Towards Scalable Electronics: Synthetic 2D Materials for Large-Area 2D Circuit Integration

EdgeAI-Aware Design of In-Memory Computing Architectures

Instabilities in Elastic and Magneto-Elastic Beams and Shells: from Shell Buckling to the Design of a Programmable Braille Reader

An Investigation of Manifold-Based Direct Control for a Brain-to-Body Neural Bypass

Deep Learning Theory Through the Lens of Diagonal Linear Networks

A story of two transitions: From adhesive to abrasive wear and from ductile to brittle regime

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

Designed Semiconductor Network Random Lasers

Chaosity: Understanding Contemporary NUMA-architectures

Bayes-optimal Learning of Deep Random Networks of Extensive-width

HetCache: Synergising NVMe Storage and GPU acceleration for Memory-Efficient Analytics

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

Physics-Informed Machine Learning for Modeling and Control of Dynamical Systems

Forest Drought Impact Prediction based on Spatio-temporal Satellite Imagery and Weather Forecasts -- A Spatio-Temporal Approach using Convolutional LSTM Models

Towards Robust Monitoring of the Laser Powder Bed Fusion Process based on Acoustic Emission combined with Machine Learning Solutions