龙星计划课程-深度学习 天津大学 7月2日-7月5日.

Slides:



Advertisements
Similar presentations
Greedy Layer-Wise Training of Deep Networks
Advertisements

Deep Learning Bing-Chen Tsai 1/21.
1 Image Classification MSc Image Processing Assignment March 2003.
Golden Age of Algorithms Prabhas Chongstitvatana Chulalongkorn University.
Stochastic Neural Networks Deep Learning and Neural Nets Spring 2015.
CS590M 2008 Fall: Paper Presentation
Stacking RBMs and Auto-encoders for Deep Architectures References:[Bengio, 2009], [Vincent et al., 2008] 2011/03/03 강병곤.
POSTER TEMPLATE BY: Multi-Sensor Health Diagnosis Using Deep Belief Network Based State Classification Prasanna Tamilselvan.
Po-Sen Huang1 Xiaodong He2 Jianfeng Gao2 Li Deng2
Deep Learning.
Optimal Adaptation for Statistical Classifiers Xiao Li.
K-means Based Unsupervised Feature Learning for Image Recognition Ling Zheng.
Deep Learning and its applications to Speech EE 225D - Audio Signal Processing in Humans and Machines Oriol Vinyals UC Berkeley.
CIAR Second Summer School Tutorial Lecture 2b Autoencoders & Modeling time series with Boltzmann machines Geoffrey Hinton.
Playing with features for learning and prediction Jongmin Kim Seoul National University.
Eigenedginess vs. Eigenhill, Eigenface and Eigenedge by S. Ramesh, S. Palanivel, Sukhendu Das and B. Yegnanarayana Department of Computer Science and Engineering.
Video Tracking Using Learned Hierarchical Features
From Machine Learning to Deep Learning. Topics that I will Cover (subject to some minor adjustment) Week 2: Introduction to Deep Learning Week 3: Logistic.
Dr. Z. R. Ghassabi Spring 2015 Deep learning for Human action Recognition 1.
2008 © ChengXiang Zhai Dragon Star Lecture at Beijing University, June 21-30, 龙星计划课程 : 信息检索 Course Summary ChengXiang Zhai ( 翟成祥 ) Department of.
Introduction to Deep Learning
Deep learning Tsai bing-chen 10/22.
Abstract Deep neural networks are becoming a fundamental component of high performance speech recognition systems. Performance of deep learning based systems.
Deep Belief Network Training Same greedy layer-wise approach First train lowest RBM (h 0 – h 1 ) using RBM update algorithm (note h 0 is x) Freeze weights.
Painting Classification by Artist and Period Using Neural Network Pattern Classification Techniques Stuart Rowan 12/12/2008.
MLSLP-2012 Learning Deep Architectures Using Kernel Modules (thanks collaborations/discussions with many people) Li Deng Microsoft Research, Redmond.
Deep Learning Overview Sources: workshop-tutorial-final.pdf
Xintao Wu University of Arkansas Introduction to Deep Learning 1.
Feature selection using Deep Neural Networks March 18, 2016 CSI 991 Kevin Ham.
Vision-inspired classification
Big data classification using neural network
Some Slides from 2007 NIPS tutorial by Prof. Geoffrey Hinton
Learning Deep Generative Models by Ruslan Salakhutdinov
Machine Learning for Data Certification at CMS
Deep Learning Amin Sobhani.
an introduction to: Deep Learning
A Personal Tour of Machine Learning and Its Applications
Deep Learning Insights and Open-ended Questions
Restricted Boltzmann Machines for Classification
Neural Networks for Machine Learning Lecture 1e Three types of learning Geoffrey Hinton with Nitish Srivastava Kevin Swersky.
Deep Learning.
Multimodal Learning with Deep Boltzmann Machines
Deep Learning Yoshua Bengio, U. Montreal
Deep Learning with TensorFlow online Training at GoLogica Technologies
Deep learning and applications to Natural language processing
Unsupervised Learning and Neural Networks
Unsupervised Learning and Autoencoders
Deep Learning Workshop
Deep Learning: Methodologies and Applications in Medical Imaging
with Daniel L. Silver, Ph.D. Christian Frey, BBA April 11-12, 2017
Artificial Neural Networks
FUNDAMENTALS OF MACHINE LEARNING AND DEEP LEARNING
Department of Electrical and Computer Engineering
كاربردهاي داده كاوي در بانكداري
Handwritten Digits Recognition
دانشگاه صنعتی امیرکبیر Instructor : Saeed Shiry & Bishop Ch. 1
Deep learning Introduction Classes of Deep Learning Networks
Deep Architectures for Artificial Intelligence
ECE 599/692 – Deep Learning Lecture 9 – Autoencoder (AE)
Deep Belief Nets and Ising Model-Based Network Construction
T H E P U B G P R O J E C T.
Representation Learning with Deep Auto-Encoder
Matt, Ridwan, and Spencer
Research Institute for Future Media Computing
LECTURE 34: Autoencoders
An introduction to: Deep Learning aka or related to Deep Neural Networks Deep Structural Learning Deep Belief Networks etc,
Review of Statistical Pattern Recognition
FOUNDATIONS OF BUSINESS ANALYTICS Introduction to Machine Learning
CRCV REU 2019 Aaron Honculada.
What is Artificial Intelligence?
Presentation transcript:

龙星计划课程-深度学习 天津大学 7月2日-7月5日

Lecturer Li Deng Microsoft Research Redmond

What is Deep Learning? A class of machine learning techniques that exploit many layers of non-linear information processing for supervised or unsupervised feature extraction and transformation, and for pattern analysis and classification.

History of Deep Learning Hinton, G. E. and Salakhutdinov, R. R  Reducing the dimensionality of data with neural networks. Science, Vol. 313. no. 5786, pp. 504 - 507, 28 July 2006.

Unsupervised feature learning

Motivated by Neuroscience

What Types of Problems Fit (not fit) Deep Learning

Models DBN (Deep belief network) BM(Boltzmann machine) RBM(Restricted Boltzmann machine) DNN(Deep neural network) Deep auto-encoder

Thank you!