Language and culture internalization for human-like autotelic AI
Building autonomous agents able to grow open-ended repertoires of skills across their lives
is a fundamental goal of artificial intelligence (AI). A promising developmental approach …
is a fundamental goal of artificial intelligence (AI). A promising developmental approach …
Autotelic agents with intrinsically motivated goal-conditioned reinforcement learning: a short survey
Building autonomous machines that can explore open-ended environments, discover
possible interactions and build repertoires of skills is a general objective of artificial …
possible interactions and build repertoires of skills is a general objective of artificial …
Safety verification for neural networks based on set-boundary analysis
Z Liang, D Ren, W Liu, J Wang, W Yang… - … Symposium on Theoretical …, 2023 - Springer
Neural networks (NNs) are increasingly applied in safety-critical systems such as
autonomous vehicles. However, they are fragile and are often ill-behaved. Consequently …
autonomous vehicles. However, they are fragile and are often ill-behaved. Consequently …
BIRDNN: Behavior-Imitation Based Repair for Deep Neural Networks
The increasing utilization of deep neural networks (DNNs) in safety-critical systems has
raised concerns about their potential to exhibit undesirable behaviors. Consequently, DNN …
raised concerns about their potential to exhibit undesirable behaviors. Consequently, DNN …
Repairing deep neural networks based on behavior imitation
The increasing use of deep neural networks (DNNs) in safety-critical systems has raised
concerns about their potential for exhibiting ill-behaviors. While DNN verification and testing …
concerns about their potential for exhibiting ill-behaviors. While DNN verification and testing …
The ecology of open-ended skill acquisition
C Moulin-Frier - 2022 - inria.hal.science
An intriguing feature of the human species is our ability to continuously invent new problems
and to proactively acquiring new skills in order to solve them: what is called open-ended skill …
and to proactively acquiring new skills in order to solve them: what is called open-ended skill …
Two-Stream Heterogeneous Graph Network with Dynamic Interactive Learning for Video Question Answering
Video question answering (VideoQA) challenges the joint learning of visual and linguistic
knowledge. Whilst the dynamic video-question interaction is not well explored in previous …
knowledge. Whilst the dynamic video-question interaction is not well explored in previous …
Verifying safety of neural networks from topological perspectives
Neural networks (NNs) are increasingly applied in safety-critical systems such as
autonomous vehicles. However, they are fragile and are often ill-behaved. Consequently …
autonomous vehicles. However, they are fragile and are often ill-behaved. Consequently …
Credit assignment for trained neural networks based on Koopman operator theory
Credit assignment problem of neural networks refers to evaluating the credit of each network
component to the final outputs. For an untrained neural network, approaches to tackling it …
component to the final outputs. For an untrained neural network, approaches to tackling it …
UR4NNV: Neural Network Verification, Under-approximation Reachability Works!
Z Liang, T Wu, R Zhao, B Xue, J Wang, W Yang… - arxiv preprint arxiv …, 2024 - arxiv.org
Recently, formal verification of deep neural networks (DNNs) has garnered considerable
attention, and over-approximation based methods have become popular due to their …
attention, and over-approximation based methods have become popular due to their …