1) Machine learning can help rationalize the "experience and intuition" of chemical research by finding patterns and exceptions from large amounts of chemical data to predict new materials and phenomena.
2) While in theory chemical structures and properties can be described by Schrodinger's equation, it is impossible to solve for realistic systems, requiring approximations. Machine learning may help address this challenge.
3) Chemists have successfully created compounds with desired properties through "experience and intuition", which involves inductive reasoning from experiments rather than purely deductive logic, incorporating serendipitous findings.
This document summarizes a doctoral thesis presentation on statistical learning theory for parameter-restricted singular models. It discusses how singular models like hierarchical and latent variable models are important in statistical model design but traditional learning theory cannot analyze the generalization error of such singular models. The presentation analyzes the generalization error of non-negative matrix factorization (NMF) and latent Dirichlet allocation (LDA) as examples of parameter-restricted singular models. It derives an upper bound for the real log-threshold of NMF which determines the generalization error of singular models, and precisely analyzes the real log-threshold of LDA by relating it to a constrained matrix factorization.
1) Machine learning can help rationalize the "experience and intuition" of chemical research by finding patterns and exceptions from large amounts of chemical data to predict new materials and phenomena.
2) While in theory chemical structures and properties can be described by Schrodinger's equation, it is impossible to solve for realistic systems, requiring approximations. Machine learning may help address this challenge.
3) Chemists have successfully created compounds with desired properties through "experience and intuition", which involves inductive reasoning from experiments rather than purely deductive logic, incorporating serendipitous findings.
This document summarizes a doctoral thesis presentation on statistical learning theory for parameter-restricted singular models. It discusses how singular models like hierarchical and latent variable models are important in statistical model design but traditional learning theory cannot analyze the generalization error of such singular models. The presentation analyzes the generalization error of non-negative matrix factorization (NMF) and latent Dirichlet allocation (LDA) as examples of parameter-restricted singular models. It derives an upper bound for the real log-threshold of NMF which determines the generalization error of singular models, and precisely analyzes the real log-threshold of LDA by relating it to a constrained matrix factorization.
2015年7月11日に
エンボディード?アプローチ研究会
http://www.geocities.jp/body_of_knowledge/
「心の科学の基礎論」研究会
http://www.isc.meiji.ac.jp/~ishikawa/kokoro.html
の共同研究会で発表した内容です。
Ref. Phenomenology of Artefacts
http://rondelionai.blogspot.jp/2014/02/phenomenology-of-artefacts.html
The English version: http://www.slideshare.net/naoyaarakawa39/humanlevel-ai-phenomenology
昨今の人工知能の要素技術である「ニューラルネットワーク(Neural Network)」は、脳研究の知見から得られた計算可能なモデルである。ニューラルネットワークを知る?使う上では脳を知らなくてもよいと思うが、技術の発展の背後には脳研究が存在する。本発表では、脳とは何かに触れ、ニューラルネットワークとの関係について概説する。
"Neural network" is one of the component technologies of AI. Its technology is brain-based Nature Inspire technology. There are many brain science behind these technologies. In this presentation, first explain "What is brain?" and outline the relationship with Neural network technologies.
58. 猫の概念の獲得(2012)
? Le et al. (2012)
? Googleのチームが1000万枚の訓練画像を用いて教師
なし学習を行い、猫を含む各種表象を獲得
Official Google Blog: Using large-scale brain simulations for machine learning and A.I. |
https://googleblog.blogspot.com/2012/06/using-large-scale-brain-simulations-for.html
59. Wu, Y., Schuster, M., Chen, Z., Le, Q. V., Norouzi, M., Macherey, W., … Dean, J. (2016).
Google’s Neural Machine Translation System: Bridging the Gap between Human and
Machine Translation. http://arxiv.org/abs/1609.08144
Googleの機械翻訳(2016)
70. ? 1990’s:成熟期
? 1988 Deep ThoughtがGMに初勝利
? 1996 Deep Blue(IBM)が世界チャンピオンKasparovに
初勝利
? マッチは(1-3)でKasparovの勝利
? 1997 Deep Blue(IBM)がKasparovにマッチで勝利(2-1)
Deep Blue
Garry Kasparov
(1963-)