本スライドは、弊社の梅本により弊社内の技術勉強会で使用されたものです。
近年注目を集めるアーキテクチャーである「Transformer」の解説スライドとなっております。
"Arithmer Seminar" is weekly held, where professionals from within and outside our company give lectures on their respective expertise.
The slides are made by the lecturer from outside our company, and shared here with his/her permission.
Arithmer株式会社は東京大学大学院数理科学研究科発の数学の会社です。私達は現代数学を応用して、様々な分野のソリューションに、新しい高度AIシステムを導入しています。AIをいかに上手に使って仕事を効率化するか、そして人々の役に立つ結果を生み出すのか、それを考えるのが私たちの仕事です。
Arithmer began at the University of Tokyo Graduate School of Mathematical Sciences. Today, our research of modern mathematics and AI systems has the capability of providing solutions when dealing with tough complex issues. At Arithmer we believe it is our job to realize the functions of AI through improving work efficiency and producing more useful results for society.
ゼロから始める深層強化学習(NLP2018講演資料)/ Introduction of Deep Reinforcement LearningPreferred Networks
?
Introduction of Deep Reinforcement Learning, which was presented at domestic NLP conference.
言語処理学会第24回年次大会(NLP2018) での講演資料です。
http://www.anlp.jp/nlp2018/#tutorial
ゼロから始める深層強化学習(NLP2018講演資料)/ Introduction of Deep Reinforcement LearningPreferred Networks
?
Introduction of Deep Reinforcement Learning, which was presented at domestic NLP conference.
言語処理学会第24回年次大会(NLP2018) での講演資料です。
http://www.anlp.jp/nlp2018/#tutorial
This document discusses Bayesian dark knowledge and matrix factorization using stochastic gradient MCMC methods. It applies various SG-MCMC methods like SGLD, SG-HMC, and SG-NHT to Bayesian dark knowledge. It also combines GANs with Bayesian dark knowledge to generate unlabeled data. Finally, it applies SG-MCMC and neural networks to probabilistic matrix factorization. Results on MNIST and movie recommendation datasets are presented.
3D Volumetric Data Generation with Generative Adversarial NetworksPreferred Networks
?
This document discusses using generative adversarial networks (GANs) to generate 3D volumetric data. Specifically, it aims to extend GANs to 3D voxel data by applying 3D convolutions and deconvolutions. To do so, it trains a GAN on chair models from a dataset, representing the 3D models as binary voxel grids. Techniques like minibatch discrimination and mutual information reconstruction are used to improve training stability and add semantic meaning. The results generated 3D chair-like models but training convergence was an issue due to the small dataset size.
The document discusses wavelet transforms and related concepts like mother wavelets, scaling functions, and two-scale relationships. It covers definitions of wavelet transforms and wavelets, properties of wavelets like orthogonality, and applications of wavelet transforms such as signal analysis and image compression. Sections 2.1 through 2.11 each explore an aspect of wavelet transforms and wavelets.
La Atención Tutorial Integral (ATI) es un proceso de acompa?amiento socioafectivo y académico para estudiantes que busca contribuir a su desarrollo integral a través de la tutoría individual y grupal. La ATI aborda dimensiones personales, de aprendizaje y sociales de los estudiantes de manera formativa y preventiva. Se implementa a través de un comité de tutoría, coordinador de tutoría, tutores, docentes y auxiliares de educación, quienes brindan orientación educativa individualizada y en grupo.
El documento describe las diferentes mezclas raciales en la sociedad virreinal, incluyendo criollos, mestizos, mulatos, zambos, cholos, castizos, moriscos y albinos, que resultaban de las combinaciones entre espa?oles, indios y personas de ascendencia africana.