36 citations
6 papers
Parallelizable Search-Space Decomposition for Large-Scale Combinatorial Optimization Problems Using Ising Machines
Eiji Kawase, Shuta Kikuchi, Hideaki Tamai +1
Combinatorial optimization problems are crucial in industry. However, many COPs are NP-hard, causing the search space to grow exponentially with problem size and rendering large-sc…
AaSP: Aliasing-aware Self-Supervised Pre-Training for Audio Spectrogram Transformers
Kohei Yamamoto, Kosuke Okusa
Transformer-based audio self-supervised learning (SSL) models commonly use spectrograms, vision-style Transformers, and masked modeling objectives. However, convolutional patchific…
Frailty Care Robot for Elderly and Its Application for Physical and Psychological Support
Yoichi Yamazaki, Masayuki Ishii, Takahiro Ito +1
To achieve continuous frail care in the daily lives of the elderly, we propose AHOBO, a frail care robot for the elderly at home. Two types of support systems by AHOBO were impleme…
A condition for the existence of zero coefficients in the powers of the determinant polynomial
Minoru Itoh, Jimpei Shimoyoshi
We discuss the existence of zero coefficients in the powers of the determinant polynomial of order . D. G. Glynn proved that the coefficients of the th power of the determina…
Learnable Companding Quantization for Accurate Low-bit Neural Networks
Kohei Yamamoto
Quantizing deep neural networks is an effective method for reducing memory consumption and improving inference speed, and is thus useful for implementation in resource-constrained…
PCAS: Pruning Channels with Attention Statistics for Deep Network Compression
Kohei Yamamoto, Kurato Maeno
Compression techniques for deep neural networks are important for implementing them on small embedded devices. In particular, channel-pruning is a useful technique for realizing co…