Kota Ando

Assistant Professor

Hokkaido University

Japan

Research Interests

Explore related searches

Professors in Japan Professors in Artificial Intelligence Artificial Intelligence professors in Japan

Contact this professor

ORCID

Google Scholar

About

Kota Ando is an Assistant Professor at Hokkaido University in Japan. His research primarily focuses on edge AI, machine learning, and neural network optimization, as evidenced by his recent publications on topics such as anomaly detection in reciprocating machines and semi-supervised learning techniques. Professor Ando is actively exploring innovative approaches in collaborative learning and predictive coding networks to enhance the efficiency and explainability of AI systems.

Kota Ando

Research Interests

Explore related searches

Contact this professor

About

Articles (18)

Variable-parallelism reconfigurable architecture for efficient and flexible CNN acceleration

Design and evaluation of analog predictive coding networks based on the free-energy principle

Common Bases Hypothesis: exploring multi-task collaborative learning of neural networks

Evaluation of the encoder-decoder model's common representation acquisition toward its application in edge computing

Multi-phase-quantization optimizer and its architecture for edge AI training

Proposal and evaluation of recurrent neural network training by multi-phase quantization optimizer

Acquisition of physical kinetics in reciprocating machines using reservoir computing for anomaly detection

BBBNN: Bernoulli binary Bayesian neural network accelerator toward edge explainable AI inference

Efficient semi-supervised learning via multi-augmentations on single samples for edge AI training

Prompt engineering for generating high-quality conversations and its evaluation

Pianissimo: A Sub-mW Class DNN Accelerator With Progressively Adjustable Bit-Precision

SPCTRE: sparsity-constrained fully-digital reservoir computing architecture on FPGA

Design and evaluation of brain-inspired predictive coding networks based on the free-energy principle for novel neuromorphic hardware

Stochastic memory device based on a bistable system model with a simple analog circuit

A novel small‐signal detection method using divergence properties of second‐order linear differential equations

Fabrication and Training of 3D Conductive Polymer Networks for Neuromorphic Wetware

TT-MLP: Tensor Train Decomposition on Deep MLPs

STATICA: A 512-Spin 0.25M-Weight Annealing Processor With an All-Spin-Updates-at-Once Architecture for Combinatorial Optimization With Complete Spin–Spin Interactions

Collaborators (3)

Tetsuya Asai

Jaehoon Yu

Megumi Akai

How do I reach out?

Meet Kite AI