Infinite-width limit of deep linear 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.

Purpose The aim of this study was to develop a novel approach for predicting the expression status of Epidermal Growth Factor Receptor (EGFR) and its subtypes in patients with Non-Small Cell Lung Cancer (NSCLC) using a Three-Dimensional Convolutional Neura ...

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 ...

Species distribution models (SDMs) aim to predict the distribution of species by relating occurrence data with environmental variables. Recent applications of deep learning to SDMs have enabled new avenues, specifically the inclusion of spatial data (envir ...

Reinforcement learning (RL) is inherently rife with non-stationarity since the states and rewards the agent observes during training depend on its changing policy. Therefore, networks in deep RL must be capable of adapting to new observations and fitting n ...

We consider on the torus the scaling limit of stochastic 2D (inviscid) fluid dynamics equations with transport noise to deterministic viscous equations. Quantitative estimates on the convergence rates are provided by combining analytic and probabilistic ar ...

With the emergence of ultra-portable ultrasound systems, the need to reduce cost and complexity of ultrasound systems has intensified. Sparse arrays, employing fewer transducer elements to acquire images, offer a viable solution by effectively minimizing d ...

De novo protein design explores uncharted sequence and structure space to generate novel proteins not sampled by evolution. A main challenge in de novo design involves crafting “designable” structural templates to guide the sequence searches toward adoptin ...

The rise of robotic body augmentation brings forth new developments that will transform robotics, human-machine interaction, and wearable electronics. Extra robotic limbs, although building upon restorative technologies, bring their own set of challenges i ...

Animal behaviour alternates between stochastic exploration and goal-directed actions, which are generated by the underlying neural dynamics. Previously, we demonstrated that the compositional Restricted Boltzmann Machine (cRBM) can decompose whole-brain ac ...

Infinite-width limit of deep linear neural networks

Chat with Graph Search

Advancing EGFR mutation subtypes prediction in NSCLC by combining 3D pretrained ConvNeXt, radiomics, and clinical features

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Multi-Scale and Multimodal Species Distribution Modeling

No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO

Quantitative convergence rates for scaling limit of SPDEs with transport noise

Sequential CNN-based Enhancement of Ultrafast Ultrasound Imaging for Sparse Arrays

Exploring “dark-matter” protein folds using deep learning

Investigating neural resource allocation in the sensorimotor control of extra limbs

The Recurrent Temporal Restricted Boltzmann Machine Captures Neural Assembly Dynamics in Whole-brain Activity