193 citations · 464 across the 21 of their papers we have counts for
21 papers
Consciousness in Artificial Intelligence: Insights from the Science of Consciousness
Patrick Butlin, Robert Long, Eric Elmoznino +16
Whether current or near-term AI systems could be conscious is a topic of scientific interest and increasing public concern. This report argues for, and exemplifies, a rigorous and…
Logical Tasks for Measuring Extrapolation and Rule Comprehension
Ippei Fujisawa, Ryota Kanai
Logical reasoning is essential in a variety of human activities. A representative example of a logical task is mathematics. Recent large-scale models trained on large datasets have…
On the link between conscious function and general intelligence in humans and machines
Arthur Juliani, Kai Arulkumaran, Shuntaro Sasai +1
In popular media, there is often a connection drawn between the advent of awareness in artificial agents and those same agents simultaneously achieving human or superhuman level in…
AI agents for facilitating social interactions and wellbeing
Hiro Taiyo Hamada, Ryota Kanai
Wellbeing AI has been becoming a new trend in individuals' mental health, organizational health, and flourishing our societies. Various applications of wellbeing AI have been intro…
Experimental Evidence that Empowerment May Drive Exploration in Sparse-Reward Environments
Francesco Massari, Martin Biehl, Lisa Meeden +1
Reinforcement Learning (RL) is known to be often unsuccessful in environments with sparse extrinsic rewards. A possible countermeasure is to endow RL agents with an intrinsic rewar…
Deep Learning and the Global Workspace Theory
Rufin VanRullen, Ryota Kanai
Recent advances in deep learning have allowed Artificial Intelligence (AI) to reach near human-level performance in many sensory, perceptual, linguistic or cognitive tasks. There i…
Non-trivial informational closure of a Bayesian hyperparameter
Martin Biehl, Ryota Kanai
We investigate the non-trivial informational closure (NTIC) of a Bayesian hyperparameter inferring the underlying distribution of an identically and independently distributed finit…
A Technical Critique of Some Parts of the Free Energy Principle
Martin Biehl, Felix A. Pollock, Ryota Kanai
We summarize the original formulation of the free energy principle, and highlight some technical issues. We discuss how these issues affect related results involving generalised co…
Information Closure Theory of Consciousness
Acer Y. C. Chang, Martin Biehl, Yen Yu +1
Information processing in neural systems can be described and analysed at multiple spatiotemporal scales. Generally, information at lower levels is more fine-grained and can be coa…
A unified strategy for implementing curiosity and empowerment driven reinforcement learning
Ildefons Magrans de Abril, Ryota Kanai
Although there are many approaches to implement intrinsically motivated artificial agents, the combined usage of multiple intrinsic drives remains still a relatively unexplored res…
Boredom-driven curious learning by Homeo-Heterostatic Value Gradients
Yen Yu, Acer Y. C. Chang, Ryota Kanai
This paper presents the Homeo-Heterostatic Value Gradients (HHVG) algorithm as a formal account on the constructive interplay between boredom and curiosity which gives rise to effe…
Being curious about the answers to questions: novelty search with learned attention
Nicholas Guttenberg, Martin Biehl, Nathaniel Virgo +1
We investigate the use of attentional neural network layers in order to learn a `behavior characterization' which can be used to drive novelty search and curiosity-based policies.…
Learning to generate classifiers
Nicholas Guttenberg, Ryota Kanai
We train a network to generate mappings between training sets and classification policies (a 'classifier generator') by conditioning on the entire training set via an attentional m…
Curiosity-driven reinforcement learning with homeostatic regulation
Ildefons Magrans de Abril, Ryota Kanai
We propose a curiosity reward based on information theory principles and consistent with the animal instinct to maintain certain critical parameters within a bounded range. Our exp…
Efficient Algorithms for Searching the Minimum Information Partition in Integrated Information Theory
Jun Kitazono, Ryota Kanai, Masafumi Oizumi
The ability to integrate information in the brain is considered to be an essential property for cognition and consciousness. Integrated Information Theory (IIT) hypothesizes that t…
Learning body-affordances to simplify action spaces
Nicholas Guttenberg, Martin Biehl, Ryota Kanai
Controlling embodied agents with many actuated degrees of freedom is a challenging task. We propose a method that can discover and interpolate between context dependent high-level…
Counterfactual Control for Free from Generative Models
Nicholas Guttenberg, Yen Yu, Ryota Kanai
We introduce a method by which a generative model learning the joint distribution between actions and future states can be used to automatically infer a control scheme for any desi…
A description length approach to determining the number of k-means clusters
Hiromitsu Mizutani, Ryota Kanai
We present an asymptotic criterion to determine the optimal number of clusters in k-means. We consider k-means as data compression, and propose to adopt the number of clusters that…
Integrated information and dimensionality in continuous attractor dynamics
Satohiro Tajima, Ryota Kanai
There has been increasing interest in the integrated information theory (IIT) ofconsciousness, which hypothesizes that consciousness is integrated information withinneuronal dynami…
Permutation-equivariant neural networks applied to dynamics prediction
Nicholas Guttenberg, Nathaniel Virgo, Olaf Witkowski +2
The introduction of convolutional layers greatly advanced the performance of neural networks on image tasks due to innately capturing a way of encoding and learning translation-inv…
Neural Coarse-Graining: Extracting slowly-varying latent degrees of freedom with neural networks
Nicholas Guttenberg, Martin Biehl, Ryota Kanai
We present a loss function for neural networks that encompasses an idea of trivial versus non-trivial predictions, such that the network jointly determines its own prediction goals…