Recurrent world models facilitate policy evolution
D Ha, J Schmidhuber - Advances in neural information …, 2018 - proceedings.neurips.cc
A generative recurrent neural network is quickly trained in an unsupervised manner to
model popular reinforcement learning environments through compressed spatio-temporal …
model popular reinforcement learning environments through compressed spatio-temporal …
Is conscious perception a series of discrete temporal frames?
PA White - Consciousness and cognition, 2018 - Elsevier
This paper reviews proposals that conscious perception consists, in whole or part, of
successive discrete temporal frames on the sub-second time scale, each frame containing …
successive discrete temporal frames on the sub-second time scale, each frame containing …
World models
D Ha, J Schmidhuber - arxiv preprint arxiv:1803.10122, 2018 - arxiv.org
We explore building generative neural network models of popular reinforcement learning
environments. Our world model can be trained quickly in an unsupervised manner to learn a …
environments. Our world model can be trained quickly in an unsupervised manner to learn a …
Language models, agent models, and world models: The law for machine reasoning and planning
Despite their tremendous success in many applications, large language models often fall
short of consistent reasoning and planning in various (language, embodied, and social) …
short of consistent reasoning and planning in various (language, embodied, and social) …
Flexible weighting of diverse inputs makes hippocampal function malleable
M Aly, NB Turk-Browne - Neuroscience Letters, 2018 - Elsevier
Classic theories of hippocampal function have emphasized its role as a dedicated memory
system, but recent research has shown that it contributes broadly to many aspects of …
system, but recent research has shown that it contributes broadly to many aspects of …
Intrinsic physical concepts discovery with Object-Centric predictive models
The ability to discover abstract physical concepts and understand how they work in the world
through observing lies at the core of human intelligence. The acquisition of this ability is …
through observing lies at the core of human intelligence. The acquisition of this ability is …
Processes of believing: Where do they come from? What are they good for?
RJ Seitz, RF Paloutzian, HF Angel - F1000Research, 2017 - pmc.ncbi.nlm.nih.gov
Despite the long scholarly discourse in Western theology and philosophy on religion,
spirituality, and faith, explanations of what a belief and what believing is are still lacking …
spirituality, and faith, explanations of what a belief and what believing is are still lacking …
TMS-induced neuronal plasticity enables targeted remodeling of visual cortical maps
V Kozyrev, R Staadt, UT Eysel… - Proceedings of the …, 2018 - National Acad Sciences
Transcranial magnetic stimulation (TMS) has become a popular clinical method to modify
cortical processing. The events underlying TMS-induced functional changes remain …
cortical processing. The events underlying TMS-induced functional changes remain …
Leveraging jumpy models for planning and fast learning in robotic domains
In this paper we study the problem of learning multi-step dynamics prediction models (jumpy
models) from unlabeled experience and their utility for fast inference of (high-level) plans in …
models) from unlabeled experience and their utility for fast inference of (high-level) plans in …
Push-pull receptive field organization and synaptic depression: mechanisms for reliably encoding naturalistic stimuli in V1
Neurons in the primary visual cortex are known for responding vigorously but with high
variability to classical stimuli such as drifting bars or gratings. By contrast, natural scenes are …
variability to classical stimuli such as drifting bars or gratings. By contrast, natural scenes are …