研究者詳細 - 八谷　大岳

講演・口頭発表等 - 八谷　大岳

分割表示66 件中 41 - 60 件目／全件表示 >>

機械学習を用いた広帯域地震動合成の試み

岡﨑智久、八谷大岳、前田宜浩、岩城麻子、藤原広行、上田修功

地震学会2018年度秋季大会 2018年10月地震学会

オートエンコーダを用いた環境地図の特徴表現と自己位置推定

脇田翔平、中村恭之、八谷大岳

ロボティクス・メカトロニクス講演会 2018年06月日本機械学会ロボティクス・メカトロニクス部門

自由領域制限による経路教示と経路計画のハイブリッド自律走行

野村雅也、中村恭之、八谷大岳

第２３回ロボティクスシンポジア 2018年03月計測自動制御学会、日本ロボット学会、日本機械学会

3Dアンカーによる距離推定とロボットナビゲーションへの応用

八谷大岳、斎藤侑輝、射手矢和真、野村雅也、中村恭之

第２３回ロボティクスシンポジア 2018年03月計測自動制御学会、日本ロボット学会、日本機械学会

透視投影アンカーを用いた特定物体の検出および距離推定

八谷大岳、斎藤侑輝、射手矢和真、中村恭之

第１８回システムインテグレーション部門講演会 2017年12月計測自動制御学会

経路教示と経路計画のハイブリッド自律走行

八谷大岳、野村雅也、脇田翔平、射手矢和真、中村恭之

つくばチャレンジ2017参加レポート集 2017年

ディープラーニングによる特定人物検出と距離推定

八谷大岳、野村雅也、脇田翔平、射手矢和真、中村恭之

つくばチャレンジ2017参加レポート集 2017年

NSH: Normality Sensitive Hashing for Anomaly Detection

Hirotaka Hachiya, Masakazu Matsugu

2013 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW) 2013年 IEEE

Locality sensitive hashing (LSH) is a computationally efficient alternative to the distance based anomaly detection. The main advantages of LSH lie in constant detection time, low memory requirement, and simple implementation. However, since the metric of distance in LSHs does not consider the property of normal training data, a naive use of existing LSHs would not perform well. In this paper, we propose a new hashing scheme so that hash functions are selected dependently on the properties of the normal training data for reliable anomaly detection. The distance metric of the proposed method, called NSH (Normality Sensitive Hashing) is theoretically interpreted in terms of the region of normal training data and its effectiveness is demonstrated through experiments on real-world data. Our results are favorably comparable to state-of-the arts with the low-level features.

Feature Selection via l₁-Penalized Squared-Loss Mutual Information (情報論的学習理論と機械学習)

JITKRITTUM Wittawat, HACHIYA Hirotaka, SUGIYAMA Masashi

電子情報通信学会技術研究報告. IBISML, 情報論的学習理論と機械学習 = IEICE technical report. IBISML, Information-based induction sciences and machine learning 2012年03月05日一般社団法人電子情報通信学会

Feature selection is a technique to screen out less important features. Many existing supervised feature selection algorithms use redundancy and relevancy as the main criteria to select features. However, feature interaction, potentially a key characteristic in real-world problems, has not received much attention. As an attempt to take feature interaction into account, we propose l_1-LSMI, an l_1-regularization based algorithm that maximizes a squared-loss variant of mutual information between selected features and outputs. Numerical results show that l_1-LSMI performs well in handling redundancy, detecting non-linear dependency, and considering feature interaction.

Efficient Sample Reuse in Policy Gradients with Parameter-based Exploration (情報論的学習理論と機械学習)

ZHAO Tingting, HACHIYA Hirotaka, SUGIYAMA Masashi

The policy gradient approach is a flexible and powerful reinforcement learning method particularly for problems with continuous actions such as robot control. A common challenge in this scenario is how to stabilize policy gradient estimates for reliable policy updates. In this paper, we combine the following three ideas and give a highly stable and practical policy gradient method: (a) the policy gradients with parameter based exploration, which is a recently proposed policy search method with high stability, (b) an importance sampling technique, which allows us to reuse previously gathered data in an unbiased way, and (c) an optimal baseline, which minimizes the variance of gradient estimates with their unbiasedness being maintained. For the proposed method, we give theoretical analysis of the variance of gradient estimates and show its usefulness through experiments.

Computationally Efficient Multi-Label Classification by Least-Squares Probabilistic Classifier (情報論的学習理論と機械学習)

NAM Hyunha, HACHIYA Hirotaka, SUGIYAMA Masashi

電子情報通信学会技術研究報告 : 信学技報 2011年11月09日一般社団法人電子情報通信学会

Multi-label classification allows a sample to belong to multiple classes simultaneously, which is often the case in real-world applications such as audio tagging, image annotation, video search, and text mining. In such a multi-label scenario, taking into account correlation between multiple labels can boost the classification accuracy. However, this in turn makes classifier training more challenging because handling multiple labels tends to induce a high-dimensional optimization problem. In this paper, we propose a highly scalable multi-label classifier based on a computationally efficient classification algorithm called the least-squares probabilistic classifier. Through experiments, we show the usefulness of our proposed method.

Relative Density-Ratio Estimation for Robust Distribution Comparison (情報論的学習理論と機械学習)

YAMADA Makoto, SUZUKI Taiji, KANAMORI Takafumi, HACHIYA Hirotaka, SUGIYAMA Masashi

電子情報通信学会技術研究報告 : 信学技報 2011年11月09日一般社団法人電子情報通信学会

Divergence estimators based on direct approximation of density-ratios without going through separate approximation of numerator and denominator densities have been successfully applied to machine learning tasks that involve distribution comparison such as outlier detection, transfer learning, and two-sample homogeneity test. However, since density-ratio functions often possess high fluctuation, divergence estimation is still a challenging task in practice. In this paper, we propose to use relative divergences for distribution comparison, which involves approximation of relative density-ratios. Since relative density-ratios are always smoother than corresponding ordinary density-ratios, our proposed method is favorable in terms of the non-parametric convergence speed. Furthermore, we show that the proposed divergence estimator has asymptotic variance independent of the model complexity under a parametric setup, implying that the proposed estimator hardly overfits even with complex models. Through experiments, we demonstrate the usefulness of the proposed approach.

Modified Newton Approach to Policy Search (情報論的学習理論と機械学習)

HACHIYA Hirotaka, MORIMURA Tetsuro, MAKINO Takaki, SUGIYAMA Masashi

電子情報通信学会技術研究報告 : 信学技報 2011年11月09日一般社団法人電子情報通信学会

The natural policy gradient method was shown to be a useful approach to policy search in reinforcement learning. However, its potential weakness is that information on returns is not reflected in the metric of natural gradients, implying that it is not adaptive to data and thus less flexible. To overcome this, we propose to use Newton's method which uses the Hessian of the expected return as a metric. However, the naive implementation of Newton's method does not guarantee the Hessian to be negative definite, which causes instability on policy updates. To cope with this problem, we propose an adaptive scheme to keep the Hessian nonnegative. We demonstrate the effectiveness of our proposed method in standard reinforcement learning tasks.

Artist agent A[2]: stroke painterly rendering based on reinforcement learning (パターン認識・メディア理解)

Xie Ning, Hachiya Hirotaka, Sugiyama Masashi

電子情報通信学会技術研究報告. PRMU, パターン認識・メディア理解 2011年08月29日一般社団法人電子情報通信学会

Artist agent A[2]: stroke painterly rendering based on reinforcement learning (情報論的学習理論と機械学習)

Xie Ning, Hachiya Hirotaka, Sugiyama Masashi

電子情報通信学会技術研究報告. IBISML, 情報論的学習理論と機械学習 = IEICE technical report. IBISML, Information-based induction sciences and machine learning 2011年08月29日一般社団法人電子情報通信学会

Artist Agent A2: Stroke Painterly Rendering Based on Reinforcement Learning

Ning Xie, Hirotaka Hachiya, Masashi Sugiyama

研究報告コンピュータビジョンとイメージメディア（CVIM） 2011年08月29日

Oriental ink painting, called Sumi-e, is one of the most appealing painting styles that has attracted artists around the world. The major challenges in computer-based Sumi-e simulation are to abstract complex scene information and draw smooth and natural brush strokes. To automatically find such strokes, we propose to model the brush as a reinforcement-learning (RL) agent, and learn desired brush-trajectories by maximizing the sum of rewards in the policy search framework. We also provide elaborate design of state space, action space, and a reward function tailored for a Sumi-e agent. The effectiveness of our proposed approach is demonstrated through simulated Sumi-e experiments.Oriental ink painting, called Sumi-e, is one of the most appealing painting styles that has attracted artists around the world. The major challenges in computer-based Sumi-e simulation are to abstract complex scene information and draw smooth and natural brush strokes. To automatically find such strokes, we propose to model the brush as a reinforcement-learning (RL) agent, and learn desired brush-trajectories by maximizing the sum of rewards in the policy search framework. We also provide elaborate design of state space, action space, and a reward function tailored for a Sumi-e agent. The effectiveness of our proposed approach is demonstrated through simulated Sumi-e experiments.

Information-maximization clustering: analytic solution and model selection (情報論的学習理論と機械学習)

Sugiyama Masashi, Yamada Makoto, Kimura Manabu, HACHIYA Hirotaka

電子情報通信学会技術研究報告. IBISML, 情報論的学習理論と機械学習 = IEICE technical report. IBISML, Information-based induction sciences and machine learning 2011年03月21日一般社団法人電子情報通信学会

A recently-proposed information-maximization clustering method (Gomes et al., NIPS2010) learns a kernel logistic regression classifier in an unsupervised manner so that mutual information between feature vectors and cluster assignments is maximized. A notable advantage of this approach is that it only involves continuous optimization of a logistic model, which is substantially easier than discrete optimization of cluster assignments. However, this method still suffers from two weaknesses: (i) manual tuning of kernel parameters is necessary, and (ii) finding a good local optimal solution is not straightforward due to the strong non-convexity of logistic-regression learning. In this paper, we first show that the kernel parameters can be systematically optimized by maximizing mutual information estimates. We then propose an alternative information-maximization clustering approach using a squared-loss variant of mutual information. This novel approach allows us to obtain clustering solutions analytically in a computationally very efficient way. Through experiments, we demonstrate the usefulness of the proposed approaches.

動的計画法によるリターン分布推定

森村哲郎, 杉山将, 鹿島久嗣, 八谷大岳, 田中利幸

電子情報通信学会技術研究報告. IBISML, 情報論的学習理論と機械学習 = IEICE technical report. IBISML, Information-based induction sciences and machine learning 2010年10月28日一般社団法人電子情報通信学会

標準的な強化学習の枠組みでは, Bellman方程式を用いてリターン(割引報酬和)の期待値を推定し,意思決定を行う.近年,我々はこの枠組みを拡張し,分布Bellman方程式を用いてリターンの分布を推定する方法を提案した.これにより,バリュー・アット・リスクなどのリスクを考慮した任意の指標に基づく意思決定が行えるようになったが,分布Bellman方程式を用いた手法の収束性などの理論的性質は末だ解明されていない.本論文では,分布Bellman方程式を動的計画法によって解いた場合,解が初期近似分布に依存せず常に真のリターン分布に収束することを証明する.さらに,リターン分布推定量のモーメントの収束率も示す.最後に,得られた理論結果から,既存のリターン分布推定法の改善方法を提案し,数値実験からその有効性を示す.

New feature selection method for reinforcement learning: conditional mutual information reveals implicit state-reward dependency (情報論的学習理論と機械学習)

Hachiya Hirotaka, Sugiyama Masashi

電子情報通信学会技術研究報告. IBISML, 情報論的学習理論と機械学習 = IEICE technical report. IBISML, Information-based induction sciences and machine learning 2010年06月07日一般社団法人電子情報通信学会

Model-free reinforcement learning (RL) is a machine learning approach to decision making in unknown environment. However, real-world RL tasks often involve high-dimensional state space, and then standard RL methods do not perform well. In this paper, we propose a new feature selection framework for coping with high dimensionality. Our proposed framework adopts conditional mutual information between state and return sequences as a feature selection criterion, allowing the evaluation of implicit state-reward dependency. The conditional mutual information is approximated by a least-squares method, which results in a computationally efficient feature selection procedure. The usefulness of the proposed method is demonstrated on simulated mobile-robot navigation experiments.

Improving Model-based Reinforcement Learning with Multitask Learning (数理モデル化と問題解決(MPS) Vol.2009-MPS-76)

SIMM JAAK, SUGIYAMA MASASHI, HACHIYA HIROTAKA

情報処理学会研究報告 2010年02月情報処理学会

　前のページ - 次のページ　

<八谷 大岳>

講演・口頭発表等 - 八谷 大岳

<八谷　大岳>

講演・口頭発表等 - 八谷　大岳