collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2025

Alice's Adventures in a Differentiable Wonderland -- Volume I, A Tour of the Land

Simone Scardapane

Neural networks surround us, in the form of large language models, speech transcription systems, molecular discovery algorithms, robotics, and much more. Stripped of anything else,…

cs.LG2025

NACHOS: Neural Architecture Search for Hardware Constrained Early Exit Neural Networks

Matteo Gambella, Jary Pomponi, Simone Scardapane +1

Early Exit Neural Networks (EENNs) endow astandard Deep Neural Network (DNN) with Early Exit Classifiers (EECs), to provide predictions at intermediate points of the processing whe…

cs.LG2024

Adaptive Computation Modules: Granular Conditional Computation For Efficient Inference

Bartosz Wójcik, Alessio Devoto, Karol Pustelnik +2

While transformer models have been highly successful, they are computationally inefficient. We observe that for each layer, the full width of the layer may be needed only for a sma…

cs.LG2024

Position: Topological Deep Learning is the New Frontier for Relational Learning

Theodore Papamarkou, Tolga Birdal, Michael Bronstein +19

Topological deep learning (TDL) is a rapidly evolving field that uses topological features to understand and design deep learning models. This paper posits that TDL is the new fron…

cs.LG2024

Conditional computation in neural networks: principles and research trends

Simone Scardapane, Alessandro Baiocchi, Alessio Devoto +3

This article summarizes principles and ideas from the emerging area of applying \textit{conditional computation} methods to the design of neural networks. In particular, we focus o…

cs.LG2024

Class incremental learning with probability dampening and cascaded gated classifier

Jary Pomponi, Alessio Devoto, Simone Scardapane

Humans are capable of acquiring new knowledge and transferring learned knowledge into different domains, incurring a small forgetting. The same ability, called Continual Learning,…