From the 1 of 5 linked papers with an AI index.
5 papers
Scalable Training of Continuous-Time Spiking Neural Networks with Differentiable Spike-Time Discretization
Yusuke Sakemi, Tomoya Takeuchi, Takeo Hosomi +1
The paper proposes a memory‑efficient training method for continuous‑time spiking neural networks by discretizing spike times into differentiable weighted events, enabling deep SNN…
Chaos-based reinforcement learning with TD3
Toshitaka Matsuki, Yusuke Sakemi, Kazuyuki Aihara
Chaos-based reinforcement learning (CBRL) is a method in which the agent's internal chaotic dynamics drives exploration. However, the learning algorithms in CBRL have not been thor…
Enhancing Time-Series Anomaly Detection by Integrating Spectral-Residual Bottom-Up Attention with Reservoir Computing
Hayato Nihei, Sou Nobukawa, Yusuke Sakemi +1
Reservoir computing (RC) establishes the basis for the processing of time-series data by exploiting the high-dimensional spatiotemporal response of a recurrent neural network to an…
Learning the Simplest Neural ODE
Yuji Okamoto, Tomoya Takeuchi, Yusuke Sakemi
Since the advent of the ``Neural Ordinary Differential Equation (Neural ODE)'' paper, learning ODEs with deep learning has been applied to system identification, time-series foreca…
Harnessing Nonidealities in Analog In-Memory Computing Circuits: A Physical Modeling Approach for Neuromorphic Systems
Yusuke Sakemi, Yuji Okamoto, Takashi Morie +3
Large-scale deep learning models are increasingly constrained by their immense energy consumption, limiting their scalability and applicability for edge intelligence. In-memory com…