ML cubeML cubeML cube

kmlcube

15 Feb 22

Reti Neurali Artificiali per Comprendere il funzionamento della Mente

Sino a pochi decenni fa, lo studio della mente e del comportamento umano erano sostanzialmente appannaggio della psicologia e la filosofia. Nonostante sia possibile identificare la nascita delle neuroscienze attorno al V secolo a.C., la disciplina moderna fiorì negli anni ’60 portando un grande contributo nella comprensione delle basi biologiche dell’apprendimento e la memoria (1). […]
Read More
15 Feb 22

Deepfake: tipologie e riflessioni, deep learning e GANs

Questo articolo vuole proporre alcuni esempi di Deepfake con tipologie e riflessioni su deep learning e GANs. Prova a immaginare un discorso di un candidato politico estremamente volgare di incitamento all’odio che viene diffuso in rete e reso virale dalle community online sui social media. Uno scenario fittizio ma realistico grazie alle tecnologie di AI […]
Read More
15 Feb 22

Federated Learning Per Predire Il Fabbisogno Di Ossigeno

L’Addenbrooke’s Hospital di Cambridge in collaborazione con NVIDIA e altri 20 ospedali sparsi nel mondo ha impiegato un algoritmo di Intelligenza Artificiale e il Federated Learning per predire il fabbisogno di ossigeno dei pazienti affetti da Covid-19 nei primi giorni di terapia. FEDERATED LEARNING: L’APPRENDIMENTO FEDERATO PER IL TRAINING ALGORITMICO L’algoritmo di AI impiegato dall’Addenbrooke’s Hospital […]
Read More
14 Feb 22

L’intelligenza Artificiale nella vita di tutti i giorni

Ogniqualvolta viene nominata l’Intelligenza Artificiale molti immaginano un futuro distopico in cui ogni singola attività viene svolta dalle macchine. Inoltre, un’opinione errata molto diffusa è il fatto che l’Intelligenza Artificiale riguardi il futuro e che non faccia ancora parte delle nostre vite. L’Intelligenza Artificiale viene invece applicata nei più diversi settori e ha indubbiamente trasformato […]
Read More
AAAI-Logo
05 Mar 21

Policy Optimization as Online Learning with Mediator Feedback

Policy Optimization as Online Learning with Mediator Feedback Authors: Alberto Maria Metelli, Matteo Papini, Pierluca D’Oro, Marcello Restelli Conference: AAAI 2021 Abstract: Policy Optimization (PO) is a widely used approach to address continuous control tasks. In this paper, we introduce the notion of mediator feedback that frames PO as an online learning problem over the […]
Read More
05 Mar 21

Task-Agnostic Exploration via Policy Gradient of a Non-Parametric State Entropy Estimate

Task-Agnostic Exploration via Policy Gradient of a Non-Parametric State Entropy Estimate Authors: Mirco Mutti, Lorenzo Pratissoli, Marcello Restelli Conference: AAAI 2021 Abstract: In a reward-free environment, what is a suitable intrinsic objective for an agent to pursue so that it can learn an optimal task-agnostic exploration policy? In this paper, we argue that the entropy […]
Read More
AAAI-Logo
18 Feb 21

Learning Probably Approximately Correct Maximin Strategies in Games with Infinite Strategy Spaces

Learning Probably Approximately Correct Maximin Strategies in Games with Infinite Strategy Spaces Authors: Alberto Marchesi, Francesco Trovò, Nicola Gatti Conference: AAAI 2021 Abstract: We tackle the problem of learning equilibria in simulationbased games. In such games, the players’ utility functions cannot be described analytically, as they are given through a black-box simulator that can be […]
Read More
AAAI-Logo
18 Feb 21

Online Learning in Non-Cooperative Configurable Markov Decision Process

Online Learning in Non-Cooperative Configurable Markov Decision Process Authors: Giorgia Ramponi, Alberto Maria Metelli, Alessandro Concetti, Marcello Restelli Conference: AAAI 2021 Abstract: In the Configurable Markov Decision Processes there are two entities, a Reinforcement Learning agent and a configurator which can modify some parameters of the environment to improve the performance of the agent. What […]
Read More
18 Feb 21

Inverse Reinforcement Learning from a Gradient-based Learner

Inverse Reinforcement Learning from a Gradient-based Learner Authors: Giorgia Ramponi, Gianluca Drappo, Marcello Restelli Conference: NeurIPS 2020 Abstract: Inverse Reinforcement Learning addresses the problem of inferring an expert’s reward function from demonstrations. However, in many applications, we not only have access to the expert’s near-optimal behaviour, but we also observe part of her learning process. […]
Read More
18 Feb 21

An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits

An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits Authors: Andrea Tirinzoni, Matteo Pirotta, Marcello Restelli, Alessandro Lazaric Conference: NeurIPS 2020 Abstract: In the contextual linear bandit setting, algorithms built on the optimism principle fail to exploit the structure of the problem and have been shown to be asymptotically suboptimal. In this paper, we […]
Read More