Deep learning in neural networks: An overview
J Schmidhuber - Neural networks, 2015 - Elsevier
In recent years, deep artificial neural networks (including recurrent ones) have won
numerous contests in pattern recognition and machine learning. This historical survey …
numerous contests in pattern recognition and machine learning. This historical survey …
On learning to think: Algorithmic information theory for novel combinations of reinforcement learning controllers and recurrent neural world models
J Schmidhuber - arXiv preprint arXiv:1511.09249, 2015 - arxiv.org
This paper addresses the general problem of reinforcement learning (RL) in partially
observable environments. In 2013, our large RL recurrent neural networks (RNNs) learned …
observable environments. In 2013, our large RL recurrent neural networks (RNNs) learned …
Self-organizing maps for storage and transfer of knowledge in reinforcement learning
T George Karimpanal, R Bouffanais - Adaptive Behavior, 2019 - journals.sagepub.com
The idea of reusing or transferring information from previously learned tasks (source tasks)
for the learning of new tasks (target tasks) has the potential to significantly improve the …
for the learning of new tasks (target tasks) has the potential to significantly improve the …
Optimized skill knowledge transfer model using hybrid Chicken Swarm plus Deer Hunting Optimization for human to robot interaction
Robots are more competent for progressing knowledge and learning new tasks that are of
demanding interest. Service robots need trouble-free programming techniques facilitating …
demanding interest. Service robots need trouble-free programming techniques facilitating …
A reinforcement learning architecture that transfers knowledge between skills when solving multiple tasks
P Tommasino, D Caligiore, M Mirolli… - IEEE Transactions on …, 2016 - ieeexplore.ieee.org
When humans learn several skills to solve multiple tasks, they exhibit an extraordinary
capacity to transfer knowledge between them. We present here the last enhanced version of …
capacity to transfer knowledge between them. We present here the last enhanced version of …
Development of improved coyote optimization with deep neural network for intelligent skill knowledge transfer for human to robot interaction
New control approaches are being developed to allow robots to undertake increasingly
dynamic and dextrous control tasks. Since these abilities need a large amount of …
dynamic and dextrous control tasks. Since these abilities need a large amount of …
Self-delimiting neural networks
J Schmidhuber - arXiv preprint arXiv:1210.0118, 2012 - arxiv.org
Self-delimiting (SLIM) programs are a central concept of theoretical computer science,
particularly algorithmic information & probability theory, and asymptotically optimal program …
particularly algorithmic information & probability theory, and asymptotically optimal program …
Behavior is everything: Towards representing concepts with sensorimotor contingencies
AI has seen remarkable progress in recent years, due to a switch from hand-designed
shallow representations, to learned deep representations. While these methods excel with …
shallow representations, to learned deep representations. While these methods excel with …
Self-organizing maps as a storage and transfer mechanism in reinforcement learning
TG Karimpanal, R Bouffanais - arXiv preprint arXiv:1807.07530, 2018 - arxiv.org
The idea of reusing information from previously learned tasks (source tasks) for the learning
of new tasks (target tasks) has the potential to significantly improve the sample efficiency …
of new tasks (target tasks) has the potential to significantly improve the sample efficiency …
Modular and hierarchical brain organization to understand assimilation, accommodation and their relation to autism in reaching tasks: a developmental robotics …
D Caligiore, P Tommasino, V Sperati… - Adaptive …, 2014 - journals.sagepub.com
By assimilation children embody sensorimotor experiences into already built mental
structures. Conversely, by accommodation these structures are changed according to the …
structures. Conversely, by accommodation these structures are changed according to the …