-
ErNESTO-gym
Standardized micro-grid environment for reinforcement learning experiments employing real-world datasets regarding energy consumption, generation, and market.-
.zip
The resource: 'ErNESTO-gym' is not accessible as guest user. You must login to access it!
-
.zip
-
CPG: Constrained Policy Gradient
CPG is a reinforcement learning algorithm thought for solving continuous control problems with user defined or structural constraints. CPG has two versions, C-PGPE and C-PGAE,... -
Best Arm Identification for Stochastic Rising Bandits
We propose two algorithms, R-UCBE and R-SR, performing best arm identification in the stochastic rising bandit setting, thought for modeling the combined algorithm selection... -
Artificial Graph Dataset Generator
This Python package generates synthetic graphs with a fixed graph edit distance. The generated datasets can be used to robustly train deep learning algorithms to compute the... -
Synchronization is All You Need - Exocentric-to-Egocentric Transfer for Tempo...
We consider the problem of transferring a temporal action segmentation system initially designed for exocentric (fixed) cameras to an egocentric scenario, where wearable... -
PREGO: Online mistake detection in PRocedural EGOcentric videos
Promptly identifying procedural errors from egocentric videos in an online setting is highly challenging and valuable for detecting mistakes as soon as they happen. This... -
EgoISM-HOI - Exploiting Multimodal Synthetic Data for Egocentric Human-Object...
We tackle the problem of Egocentric Human-Object Interaction (EHOI) detection in an industrial domain. To overcome the lack of public datasets in this context, we propose a... -
AFF-ttention! - Affordances and Attention models for Short-Term Object Intera...
Short-Term object-interaction Anticipation (STA) consists of detecting the location of the next-active objects, the noun and verb categories of the interaction, and the time... -
Neural Networks for Sparse Grid-Based Discontinuity Detectors
In this repository, we publish the codes necessary to load and use the NN-based discontinuity detectors, presented for the first time in the preprint: Graph-Informed Neural... -
Onboard deep lossless and near-lossless predictive coding of hyperspectral im...
Code for "Onboard deep lossless and near-lossless predictive coding of hyperspectral images with line-based attention" paper. The method implements a low-complexity neural... -
Private neuroAnDetect
Semi-supervised approach to anomaly detection for neuro-imaging. The method generates segmentation of abnormal tissues that can be used to support medical reporting. The... -
Private ASPen: ASP-based Implementation for Collective Entity Resolution
This is an Answer Set Programming (ASP) encoding for LACE, which is a novel declarative approach to Collective Entity Resolution in the classical relational database setting.... -
Fuzzy Logic Visual Network (FLVN): A neuro-symbolic approach for visual featu...
Neuro-symbolic integration aims at harnessing the power of symbolic knowledge representation combined with the learning capabilities of deep neural networks. In particular,... -
A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task P...
Human comprehension of a video stream is naturally broad: in a few instants, we are able to understand what is happening, the relevance and relationship of objects, and... -
PEM: Prototype-based Efficient MaskFormer for Image Segmentation
Prototype-based Efficient MaskFormer (PEM) is an efficient transformer-based architecture that can operate in multiple segmentation tasks. PEM proposes a novel prototype-based... -
Bringing Online Egocentric Action Recognition into the wild
To enable a safe and effective human-robot cooperation, it is crucial to develop models for the identification of human activities. Egocentric vision seems to be a viable... -
Private Multi-Start Optimization Neural Networks
In this repository, we publish the codes necessary to implement the Multi-Start Optimization Neural Networks (MSO-NNs), presented fin the paper: Automatic... -
Graph-Informed Neural Networks
In this repository, we publish the codes necessary to implement the Graph-Informed Neural Networks (GINNs), presented for the first time in the paper: Graph-Informed Neural... -
Private Alternate Training for Multi-Task Neural Networks
In this repository, we publish the code used to implement the Alternate Training through the Epochs (ATE) procedure for training Multi-Task Neural Networks (MTNN) presented in... -
Private Dynamical Linear Upper Confidence Bound (DynLin-UCB)
The repository contains the code to run DynLin-UCB (Dynamical Linear Upper Confidence Bound). DynLin-UCB is an optimistic regret-minimization algorithm that can be used to...
