The document contains mathematical equations and notation related to machine learning and probability distributions. It involves defining terms like P(y|x), which represents the probability of outcome y given x, and exploring ways to calculate the expected value of an objective function Rn under different probability distributions p and q over the variables x and y. The goal appears to be to select parameters θ to optimize some objective while accounting for the distributions of the training data.
The detailed results are described at GitHub (in English):
https://github.com/jkatsuta/exp-18-1q
(maddpg/experiments/my_notes/のexp1 ~ exp6)
立教大学のセミナー資料(前篇)です。
資料後篇:
/JunichiroKatsuta/ss-108099542
ブログ(動画あり):
https://recruit.gmo.jp/engineer/jisedai/blog/multi-agent-reinforcement-learning/
Amazon SageMaker is a fully managed service that enables developers and data scientists to build, train, and deploy machine learning (ML) models quickly. It provides algorithms, notebooks, APIs and scalable infrastructure for building ML models. Some key features of SageMaker include algorithms for common ML tasks, notebooks for developing models, APIs for training and deployment, and scalable infrastructure for training and hosting models. It also integrates with other AWS services like S3, EC2 and VPC.
The document outlines strategies for enhancing research efficiency, emphasizing the importance of effective literature review, management skills, and collaborative efforts among researchers. It discusses two main methods for skill enhancement: learning from peers and leveraging online resources, while highlighting the challenges and advantages of each approach. Additionally, it provides insights into the dynamics of various research labs, communication practices, and the value of sharing knowledge across institutions.
北村大地, 小野順貴, "独立性基準を用いた非負値行列因子分解の効果的な初期値決定法," 日本音響学会 2016年春季研究発表会, 3-3-5, pp. 619-622, Kanagawa, March 2016.
Daichi Kitamura, Nobutaka Ono, "Statistical-independence-based effective initialization for nonnegative matrix factorization," Proceedings of 2016 Spring Meeting of Acoustical Society of Japan, 3-3-5, pp. 619-622, Kanagawa, March 2016 (in Japanese).
Amazon SageMaker is a fully managed service that enables developers and data scientists to build, train, and deploy machine learning (ML) models quickly. It provides algorithms, notebooks, APIs and scalable infrastructure for building ML models. Some key features of SageMaker include algorithms for common ML tasks, notebooks for developing models, APIs for training and deployment, and scalable infrastructure for training and hosting models. It also integrates with other AWS services like S3, EC2 and VPC.
The document outlines strategies for enhancing research efficiency, emphasizing the importance of effective literature review, management skills, and collaborative efforts among researchers. It discusses two main methods for skill enhancement: learning from peers and leveraging online resources, while highlighting the challenges and advantages of each approach. Additionally, it provides insights into the dynamics of various research labs, communication practices, and the value of sharing knowledge across institutions.
北村大地, 小野順貴, "独立性基準を用いた非負値行列因子分解の効果的な初期値決定法," 日本音響学会 2016年春季研究発表会, 3-3-5, pp. 619-622, Kanagawa, March 2016.
Daichi Kitamura, Nobutaka Ono, "Statistical-independence-based effective initialization for nonnegative matrix factorization," Proceedings of 2016 Spring Meeting of Acoustical Society of Japan, 3-3-5, pp. 619-622, Kanagawa, March 2016 (in Japanese).
On Sept. 4, 2010 at XP Matsuri, Kenji Hiranabe talked about the current situation of Agile and XP. Covers history of Patterns and Agile, Lean and recent Kanban movements, and goes back to XP. Explores what was the thing called "XP" with love.
Understand the AI-powered test automation with Magic PodNozomi Ito
?
This document outlines a workshop agenda for understanding AI-powered test automation using Magic Pod, covering its introduction, basic and practical exercises, and technical details. The workshop aims to familiarize participants with Magic Pod's functionality, including creating and managing test cases for applications, as well as utilizing machine learning technologies to enhance test automation. Key topics include setting up the Magic Pod environment, performing various exercises, and exploring the future of test automation with AI.
基礎からわかる、機械学習のソフトウェアテストのへの適用例 - 「Bag Of Words」を使った「類似チケットの検索」Nozomi Ito
?
This document discusses bag-of-words, a technique in natural language processing where a text is represented as the bag (multiset) of its words, disregarding grammar and even word order but keeping multiplicity. The document provides examples of how bag-of-words works by taking text samples and representing them as vectors of word counts. It also discusses how to calculate the similarity between two text samples represented as bag-of-words vectors using cosine similarity.
35. p 画像解析
1. 領域分割(独自ロジック)
2. 各領域をCNNにかけて物体認識
3. OCR(文字認識)
4. Captioning
5. 2. 3. 4.の結果をマージして表示
p 1.& 2. が時代遅れ&低速なので改善したい。。
n Fast R-CNN
n Faster R-CNN
n Single Shot MultiBox Detector
画像解析の全体像
40. p どう学習されたかは、人間にはブラックボックス
n 意図せぬ結果が時々起きる
p 学習ロジックの中に、ランダム処理がある(ことが多い)
n 例:確率的勾配降下法:学習データの偏りをなくすため、毎回
データをランダムに選んで学習
n 「データもロジックも変えてないのに、学習し直したら結果が
変わった!」みたいなことが..
原因
42. p 失敗することはあるか
n わかりやすいアイコン等の識別は、通常失敗しない
n 人間も判断に困るような際どいデータの判定は、学習ごとに
結果が変わりがち
p 失敗した時の対策
n 対策1:間違えたデータを学習データに加える
n 対策2:とりあえず再学習
n 対策3:諦める
n 対策4:機械学習ロジック自体の改良
基本テストケースが失敗したら