Adaptive Semantic Token Communication for Transformer-based Edge Inference
202614 publications
Graph transformer and mixture of experts for rare signal detection in calorimeter data
Comparative evaluation of CNN and ViT architectures for the petrographic classification of Levantine ceramic micrographs
A Survey on Dynamic Neural Networks: from Computer Vision to Multi-modal Sensor Fusion
A Multi-View Deep Learning Framework for Urban Tree Health Assessment via Fusion of Aerial Multispectral and Street-Level RGB Imagery
Attention Sinks in Diffusion Language Models
Lift me up: the impact of liftings on hypergraph neural networks
LRCC: Generalizing Low-rank Compression with Conditional Computation
MASS: MoErging through Adaptive Subspace Selection
Universal Properties of Activation Sparsity in Modern Large Language Models
Enhancing High-Energy Particle Physics Collision Analysis Through Graph Data Attribution Techniques
Authorship attribution and aesthetic evaluation of AI poetry: a case study with Haiku
Local Diagnostics of Learned Event Representations for Anomaly Detection at the HL-LHC
Subliminal Clocks: Latent Time Modelling in Diffusion Language Models
202523 publications
Adaptive token selection for scalable point cloud transformers
Adaptive Layer Selection for Efficient Vision Transformer Fine-Tuning
Bringing AI to Clinicians: Simplifying Pleural Effusion Cytology Diagnosis with User-Friendly Models
Cascaded Scaling Classifier: class incremental learning with probability scaling
A data attribution approach for unsupervised anomaly detection on multivariate time series
Graph State-Space Models for Spatio-Temporal Renewable Energy Forecasting
Hypergraph Neural Networks through the Lens of Message Passing: A Common Perspective to Homophily and Architecture Design
Influence based explainability of brain tumors segmentation in multimodal Magnetic Resonance Imaging
Interpretable Classification of Levantine Ceramic Thin Sections via Neural Networks
Micrographia in Parkinson's Disease: Automatic Recognition through Artificial Intelligence
Mixture-of-Experts Graph Transformers for Interpretable Particle Collision Detection
NACHOS: Neural Architecture Search for Hardware Constrained Early Exit Neural Networks
Spatio-temporal transformers for decoding neural movement control
TopoBench: A Framework for Benchmarking Topological Deep Learning
Towards zero-shot learning in 3D change detection: improving generalization with custom augmentations and evaluation
Adaptive Computation Modules: Granular Conditional Computation For Efficient Inference
How to Connect Speech Foundation Models and Large Language Models? What Matters and What Does Not
Exploring the Application of Interpretable Neural Networks for the Petrographic Classification of Ceramic Samples from the Levant
Q-Filters: Leveraging QK Geometry for Efficient KV Cache Compression
Task Singular Vectors: Reducing Task Interference in Model Merging
Topological Deep Learning with State-Space Models: A Mamba Approach for Simplicial Complexes
Communication Efficient Split Learning of ViTs with Attention-based Double Compression
Q-Filters: Leveraging QK Geometry for Efficient KV Cache Compression
202415 publications
Alice's Adventures in a Differentiable Wonderland -- Volume I, A Tour of the Land
A Meta-Learning Approach for Training Explainable Graph Neural Networks
Conditional computation in neural networks: principles and research trends
TopoX: A Suite of Python Packages for Machine Learning on Topological Domains
Adaptive Semantic Token Selection for AI-native Goal-oriented Communications
Assessing the Adaptability of Self-Supervised Learning Methods for Small-Scale Hyperspectral Imaging
Urban 3D Change Detection with Deep Learning: Custom Data Augmentation Techniques
Extended abstract No. EGU24-9729
Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion
Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion
Goal-oriented Communications based on Recursive Early Exit Neural Networks
Goal-Oriented and Semantic Communication in 6G AI-Native Networks: The 6G-GOALS Approach
From Latent Graph to Latent Topology Inference: Differentiable Cell Complex Module
Position: Topological Deep Learning is the New Frontier for Relational Learning
A Simple and Effective L2 Norm-Based Strategy for KV Cache Compression
Interpreting Temporal Graph Neural Networks with Koopman Theory
202326 publications
Guest Editorial: Trends in Reservoir Computing
Continual Barlow Twins: continual self-supervised learning for remote sensing semantic segmentation
Convergent Approaches to AI Explainability for HEP Muonic Particles Pattern Recognition
Drop Edges and Adapt: a Fairness Enforcing Fine-tuning for Graph Neural Networks
Explainable Spatio-Temporal Graph Neural Networks for multi-site photovoltaic energy production
Inferring 3D change detection from bitemporal optical images
Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence
Continual Learning with Invertible Generative Models
Learning Speech Emotion Representations in the Quaternion Domain
A New Class of Efficient Adaptive Filters for Online Nonlinear Modeling
Probabilistic load forecasting with Reservoir Computing
Rearranging pixels is a powerful black-box attack for RGB and infrared deep learning models.
Re-identification of objects from aerial photos with hybrid siamese neural networks
On the robustness of vision transformers for in-flight monocular depth estimation
Towards Artificial Intelligence Applications in Next Generation Cytopathology
Machine Un-learning: An Overview of Techniques, Applications, and Future Directions
Combining Stochastic Explainers and Subgraph Neural Networks can Increase Expressivity and Interpretability
Continual Self-Supervised Learning in Earth Observation with Embedding Regularization
EGG-GAE: scalable graph neural networks for tabular data imputation
Explainability in subgraphs-enhanced Graph Neural Networks
GeoMultiTaskNet: remote sensing unsupervised domain adaptation using geographical coordinates
New trends in urban change detection: detecting 3D changes from bitemporal optical images
Extended abstract No. EGU23-13357
ICML 2023 Topological Deep Learning Challenge : Design and Results
Tracin in Semantic Segmentation of Tumor Brains in MRI, an Extended Approach
ArcheoWeedNet: Weed Classification in the Parco archeologico del Colosseo
Convolutional Neural Networks for the Detection of Esca Disease Complex in Asymptomatic Grapevine Leaves
202210 publications
FairDrop: Biased Edge Dropout for Enhancing Fairness in Graph Representation Learning
A Probabilistic Re-Intepretation of Confidence Scores in Multi-Exit Models
Centroids Matching: an efficient Continual Learning approach operating in the embedding space
Handwriting Declines with Human Ageing: A Machine Learning Study
Self-supervised learning for medieval handwriting identification: A case study from the Vatican Apostolic Library
Evaluating Adversarial Attacks and Defences in Infrared Deep Learning Monitoring Systems
Multi-site Forecasting of Energy Time Series with Spatio-Temporal Graph Neural Networks
Pixle: a fast and effective black-box attack based on rearranging pixels
Towards Self-Supervised Gaze Estimation
Engagement Detection with Multi-Task Training in E-Learning Environments
20218 publications
Bayesian Neural Networks With Maximum Mean Discrepancy Regularization
Distributed Training of Graph Convolutional Networks
Adaptive Propagation Graph Convolutional Network
A Calibrated Multiexit Neural Network for Detecting Urothelial Cancer Cells
MARE: Self-Supervised Multi-Attention REsu-Net for Semantic Segmentation in Remote Sensing
Reservoir computing approaches for representation and classification of multivariate time series
Structured Ensembles: an Approach to Reduce the Memory Footprint of Ensemble Methods
Avalanche: an End-to-End Library for Continual Learning
202019 publications
Complex-valued Neural Networks with Non-parametric Activation Functions
Compressing deep quaternion neural networks with targeted regularization
Efficient Continual Learning in Neural Networks with Embedding Regularization
Missing Data Imputation with Adversarially-trained Graph Convolutional Networks
A Non-parametric Softmax for Improving Neural Attention in Time-Series Forecasting
Optimized Training and Scalable Implementation of Conditional Deep Neural Networks with Early Exits for Fog-supported IoT applications
Why should we add early exits to neural networks?
Differentiable Branching In Deep Networks for Fast Inference
Distributed Stochastic Nonconvex Optimization and Learning based on Successive Convex Approximation
Frontiers in Reservoir Computing
Pseudo-Rehearsal for Continual Learning with Normalizing Flows
Quaternion Neural Networks for 3D Sound Source Localization in Reverberant Environments
Recognition of marine seismic data features using convolutional neural networks
A Wide Multimodal Dense U-Net for Fast Magnetic Resonance Imaging
Deep randomized neural networks
Efficient data augmentation using graph imputation neural networks
Flexible Generative Adversarial Networks with Non-parametric Activation Functions
A Multimodal Deep Network for the Reconstruction of T2W MR Images
Music Genre Classification Using Stacked Auto-Encoders
20198 publications
Kafnets: kernel-based non-parametric activation functions for neural networks
A Multimodal Dense U-Net For Accelerating Multiple Sclerosis MRI
Quaternion Convolutional Neural Networks for Detection and Localization of 3D Sound Events
Widely Linear Kernels for Complex-Valued Kernel Activation Functions
Learning activation functions from data using cubic spline interpolation
A Low-Complexity Linear-in-the-Parameters Nonlinear Filter for Distorted Speech Signals
Multikernel activation functions: formulation and a case study
Separation of Drum and Bass from Monaural Tracks
20188 publications
Bayesian Random Vector Functional-Link Networks for Robust Data Modeling
Stochastic Training of Neural Networks via Successive Convex Approximations
Bidirectional deep-readout echo state networks
Combined Sparse Regularization for Nonlinear Adaptive Filters
Improving Graph Convolutional Networks with Non-Parametric Activation Functions
Recurrent Neural Networks with Flexible Gates using Kernel Activation Functions
Sparse Functional Link Adaptive Filter Using an ℓ1-Norm Regularization
Adaptation and learning over networks for nonlinear system modeling
201710 publications
Advances in Biologically Inspired Reservoir Computing [Guest Editorial]
A Framework for Parallel and Distributed Training of Neural Networks
Fully Decentralized Semi-supervised Learning via Privacy-preserving Matrix Completion
Group Sparse Regularization for Deep Neural Networks
Randomness in neural networks: an overview
In Codice Ratio: OCR of Handwritten Latin Documents using Deep Convolutional Networks
Recursive Multikernel Filters Exploiting Nonlinear Temporal Structure
On the Use of Deep Recurrent Neural Networks for Detecting Audio Spoofing Attacks
Effective Blind Source Separation Based on the Adam Algorithm
Privacy-Preserving Data Mining for Distributed Medical Scenarios
201612 publications
Semi-supervised Echo State Networks for Audio Classification
A decentralized training algorithm for Echo State Networks in distributed big data applications
Distributed semi-supervised support vector machines
Granular Computing Techniques for Classification and Semantic Characterization of Structured Data
A Semi-supervised Random Vector Functional-Link Network based on the Transductive Framework
Distributed reservoir computing with sparse readouts
Diffusion Spline Adaptive Filtering
Distributed Spectral Clustering based on Euclidean Distance Matrix Completion
Parallel and Distributed Training of Neural Networks via Successive Convex Approximation
Benchmarking Functional Link Expansions for Audio Classification Tasks
A Comparison of Consensus Strategies for Distributed Learning of Random Vector Functional-Link Networks
A Nonlinear Acoustic Echo Canceller with Improved Tracking Capabilities
201510 publications
Distributed Learning for Random Vector Functional-Link Networks
Improving nonlinear modeling capabilities of functional link adaptive filters
Microphone Array Based Classification for Security Monitoring in Unstructured Environments
Online Sequential Extreme Learning Machine With Kernels
Prediction of telephone calls load using Echo State Network with exogenous variables
Distributed Music Classification Using Random Vector Functional-Link Nets
Functional Link Expansions for Nonlinear Modeling of Audio and Speech Signals
Learning from Distributed Data Sources Using Random Vector Functional-Link Networks
Online Selection of Functional Links for Nonlinear System Identification
Significance-Based Pruning for Reservoir’s Neurons in Echo State Networks
20145 publications
An effective criterion for pruning reservoir’s connections in Echo State Networks
GP-based kernel evolution for L2-Regularization Networks
An interpretable graph-based image classifier
A Preliminary Study on Transductive Extreme Learning Machines
Proportionate Algorithms for Blind Source Separation
20136 publications
Convex combination of MIMO filters for multichannel acoustic echo cancellation
A Framework for Adaptive Real-Time Loudness Control
Interactive quality enhancement in acoustic echo cancellation
Music classification using extreme learning machines
User-Driven Quality Enhancement for Audio Signal Processing
PM10 Forecasting Using Kernel Adaptive Filtering: An Italian Case Study
No publications match this filter.