The design of interpretable deep learning models working in relational
d...
Deep learning methods are highly accurate, yet their opaque decision pro...
Knowledge Graph Embeddings (KGE) have become a quite popular class of mo...
Neural-symbolic AI (NeSy) allows neural networks to exploit symbolic
bac...
Safe Reinforcement learning (Safe RL) aims at learning optimal policies ...
Deploying AI-powered systems requires trustworthy models supporting effe...
We present VAEL, a neuro-symbolic generative model integrating variation...
Neural-symbolic and statistical relational artificial intelligence both
...
Recent advances in neural symbolic learning, such as DeepProbLog, extend...
Neuro-symbolic methods integrate neural architectures, knowledge
represe...
There are situations in which an agent should receive rewards only after...
Several real-world applications are characterized by data that exhibit a...
Neuro-symbolic and statistical relational artificial intelligence both
i...
In this paper we study a constraint-based representation of neural netwo...
In many real world applications, data are characterized by a complex
str...
Deep learning has been shown to achieve impressive results in several ta...
We consider a scenario where an artificial agent is reading a stream of ...
Deep learning has been shown to achieve impressive results in several do...
In the last few years, neural networks have been intensively used to dev...
Deep learning has been shown to achieve impressive results in several do...
We introduce Neural Markov Logic Networks (NMLNs), a statistical relatio...
In spite of the amazing results obtained by deep learning in many
applic...
Deep learning is very effective at jointly learning feature representati...
By and large, Backpropagation (BP) is regarded as one of the most import...
The effectiveness of deep neural architectures has been widely supported...
In the last few years the systematic adoption of deep learning to visual...