5 papers
Soft Bayesian Context Tree Models for Real-Valued Time Series
Shota Saito, Yuta Nakahara, Toshiyasu Matsushima
This paper proposes the soft Bayesian context tree model (Soft-BCT), which is a novel BCT model for real-valued time series. The Soft-BCT considers soft (probabilistic) splits of t…
A Mixture Autoregressive Image Generative Model on Quadtree Regions for Gaussian Noise Removal via Variational Bayes and Gradient Methods
Shota Saito, Yuta Nakahara, Kohei Horinouchi +3
This paper addresses the problem of image denoising for grayscale images. We propose a probabilistic image generative model that combines a quadtree region-partitioning model with…
A Lower Bound for the Number of Linear Regions of Ternary ReLU Regression Neural Networks
Yuta Nakahara, Manabu Kobayashi, Toshiyasu Matsushima
With the advancement of deep learning, reducing computational complexity and memory consumption has become a critical challenge, and ternary neural networks (NNs) that restrict par…
Variable Splitting Binary Tree Models Based on Bayesian Context Tree Models for Time Series Segmentation
Yuta Nakahara, Shota Saito, Kohei Horinouchi +4
We propose a variable splitting binary tree (VSBT) model based on Bayesian context tree (BCT) models for time series segmentation. Unlike previous applications of BCT models, the t…
Variational Bayesian Methods for a Tree-Structured Stick-Breaking Process Mixture of Gaussians by Application of the Bayes Codes for Context Tree Models
Yuta Nakahara
The tree-structured stick-breaking process (TS-SBP) mixture model is a non-parametric Bayesian model that can represent tree-like hierarchical structures among the mixture componen…