28 citations · 46 across the 12 of their papers we have counts for
12 papers
Memory Determines Learning Direction: A Theory of Gradient-Based Optimization in State Space Models
JingChuan Guan, Tomoyuki Kubota, Yasuo Kuniyoshi +1
State space models (SSMs) have gained attention by showing potential to outperform Transformers. However, previous studies have not sufficiently addressed the mechanisms underlying…
Multifunctional physical reservoir computing in soft tensegrity robots
Ryo Terajima, Katsuma Inoue, Kohei Nakajima +1
Recent studies have demonstrated that the dynamics of physical systems can be utilized for the desired information processing under the framework of physical reservoir computing (P…
Haptic Perception via the Dynamics of Flexible Body Inspired by an Ostrich's Neck
Kazashi Nakano, Katsuma Inoue, Yasuo Kuniyoshi +1
In biological systems, both skin sensitivity and body flexibility play crucial roles in haptic perception. Fully soft robots often suffer from structural fragility and delayed sens…
Attractor-merging Crises and Intermittency in Reservoir Computing
Tempei Kabayama, Motomasa Komuro, Yasuo Kuniyoshi +2
Reservoir computing can embed attractors into random neural networks (RNNs), generating a ``mirror'' of a target attractor because of its inherent symmetrical constraints. In these…
Backpropagation through Soft Body: Investigating Information Processing in Brain-Body Coupling Systems
Hiroki Tomioka, Katsuma Inoue, Yasuo Kuniyoshi +1
Animals achieve sophisticated behavioral control through dynamic coupling of the brain, body, and environment. Accordingly, the co-design approach, in which both the controllers an…
Training Spiking Neural Networks via Augmented Direct Feedback Alignment
Yongbo Zhang, Katsuma Inoue, Mitsumasa Nakajima +3
Spiking neural networks (SNNs), the models inspired by the mechanisms of real neurons in the brain, transmit and represent information by employing discrete action potentials or sp…
How noise affects memory in linear recurrent networks
JingChuan Guan, Tomoyuki Kubota, Yasuo Kuniyoshi +1
The effects of noise on memory in a linear recurrent network are theoretically investigated. Memory is characterized by its ability to store previous inputs in its instantaneous st…
Informational Embodiment: Computational role of information structure in codes and robots
Alexandre Pitti, Kohei Nakajima, Yasuo Kuniyoshi
The body morphology plays an important role in the way information is perceived and processed by an agent. We address an information theory (IT) account on how the precision of sen…
Exploiting Chaotic Dynamics as Deep Neural Networks
Shuhong Liu, Nozomi Akashi, Qingyao Huang +2
Chaos presents complex dynamics arising from nonlinearity and a sensitivity to initial states. These characteristics suggest a depth of expressivity that underscores their potentia…
Embedding bifurcations into pneumatic artificial muscle
Nozomi Akashi, Yasuo Kuniyoshi, Taketomo Jo +4
Harnessing complex body dynamics has been a long-standing challenge in robotics. Soft body dynamics is a typical example of high complexity in interacting with the environment. An…
Physical Deep Learning with Biologically Plausible Training Method
Mitsumasa Nakajima, Katsuma Inoue, Kenji Tanaka +3
The ever-growing demand for further advances in artificial intelligence motivated research on unconventional computation based on analog physical devices. While such computation de…
Transient Chaos in BERT
Katsuma Inoue, Soh Ohara, Yasuo Kuniyoshi +1
Language is an outcome of our complex and dynamic human-interactions and the technique of natural language processing (NLP) is hence built on human linguistic activities. Bidirecti…