Search Results for author:
Found 16 papers, 9 papers with code
DeepDFA: Automata Learning through Neural Probabilistic Relaxations
In this work, we introduce DeepDFA, a novel approach to identifying Deterministic Finite Automata (DFAs) from traces, harnessing a differentiable yet discrete model.
Neural Reward Machines
Non-markovian Reinforcement Learning (RL) tasks are very hard to solve, because agents must consider the entire history of state-action pairs to act rationally in the environment.
Towards a fuller understanding of neurons with Clustered Compositional Explanations
Compositional Explanations is a method for identifying logical formulas of concepts that approximate the neurons' behavior.
State of the Art of Visual Analytics for eXplainable Deep Learning
The survey concludes by identifying future research challenges and bridging activities that are helpful to strengthen the role of Visual Analytics as effective support for eXplainable Deep Learning and to foster the adoption of Visual Analytics solutions in the eXplainable Deep Learning community.
Prototype-based Interpretable Graph Neural Networks
We then evaluate the explanations of the interpretable models by comparing them with post-hoc approaches and self-explainable models.
A self-interpretable module for deep image classification on small data
This paper presents Memory Wrap, a module (i. e, a set of layers) that can be added to deep learning models to improve their performance and interpretability in settings where few data are available.
Molecule Generation from Input-Attributions over Graph Convolutional Networks
It is well known that Drug Design is often a costly process both in terms of time and economic effort.
Semi-Supervised GCN for learning Molecular Structure-Activity Relationships
Since the introduction of artificial intelligence in medicinal chemistry, the necessity has emerged to analyse how molecular property variation is modulated by either single atoms or chemical groups.
Detection Accuracy for Evaluating Compositional Explanations of Units
The recent success of deep learning models in solving complex problems and in different domains has increased interest in understanding what they learn.
Memory Wrap: a Data-Efficient and Interpretable Extension to Image Classification Models
Due to their black-box and data-hungry nature, deep learning techniques are not yet widely adopted for real-world applications in critical domains, like healthcare and justice.
Reinforcement Learning for Optimization of COVID-19 Mitigation policies
The year 2020 has seen the COVID-19 virus lead to one of the worst global pandemics in history.
Explainable Inference on Sequential Data via Memory-Tracking
Our results show that we are able to explain agent’s decisions in (1) and to reconstruct the most relevant sentences used by the network to select the story ending in (2).
DOP: Deep Optimistic Planning with Approximate Value Function Evaluation
To alleviate this problem, we present DOP, a deep model-based reinforcement learning algorithm, which exploits action values to both (1) guide the exploration of the state space and (2) plan effective policies.
Model-based Reinforcement Learning
reinforcement-learning
+2
Q-CP: Learning Action Values for Cooperative Planning
Research on multi-robot systems has demonstrated promising results in manifold applications and domains.
Learning Human-Robot Handovers Through $π$-STAM: Policy Improvement With Spatio-Temporal Affordance Maps
Human-robot handovers are characterized by high uncertainty and poor structure of the problem that make them difficult tasks.
Robotics
Knowledge Representation for Robots through Human-Robot Interaction
The representation of the knowledge needed by a robot to perform complex tasks is restricted by the limitations of perception.
