Deep Learning Tutorial

Slides:



Advertisements
Similar presentations
Spatial Pyramid Pooling in Deep Convolutional
Advertisements

Deep Learning for Big Data P. Baldi University of California, Irvine Department of Computer Science Institute for Genomics and Bioinformatics Center for.
Comp 5013 Deep Learning Architectures Daniel L. Silver March,
A shallow introduction to Deep Learning
Deep face recognition Omkar M. Parkhi, Andrea Vedaldi, Andrew Zisserman.
School of Engineering and Computer Science Victoria University of Wellington Copyright: Peter Andreae, VUW Image Recognition COMP # 18.
Deep Convolutional Nets
GENDER AND AGE RECOGNITION FOR VIDEO ANALYTICS SOLUTION PRESENTED BY: SUBHASH REDDY JOLAPURAM.
PANDA: Pose Aligned Networks for Deep Attribute Modeling Ning Zhang 1,2 Manohar Paluri 1 Marć Aurelio Ranzato 1 Trevor Darrell 2 Lumbomir Boudev 1 1 Facebook.
Deep Residual Learning for Image Recognition
Introduction to Convolutional Neural Networks
Dictionary Representation of Deep Features for Robust Face Recognition
Brief Intro to Machine Learning CS539
Comparing TensorFlow Deep Learning Performance Using CPUs, GPUs, Local PCs and Cloud Pace University, Research Day, May 5, 2017 John Lawrence, Jonas Malmsten,
Deep Learning for Big Data
Wenchi MA CV Group EECS,KU 03/20/2017
Deep Learning and Its Application to Signal and Image Processing and Analysis Class III - Fall 2016 Tammy Riklin Raviv, Electrical and Computer Engineering.
Recent developments in object detection
CNN architectures Mostly linear structure
Neural networks and support vector machines
Deep Residual Learning for Image Recognition
Deep Learning: What is it good for? R. Burgmann
The Relationship between Deep Learning and Brain Function
Machine Learning for Big Data
Compact Bilinear Pooling
Data Mining, Neural Network and Genetic Programming
Intro to Machine Learning
Convolutional Neural Fabrics by Shreyas Saxena, Jakob Verbeek
The Problem: Classification
Deep Learning Insights and Open-ended Questions
Perceptual Loss Deep Feature Interpolation for Image Content Changes
Deep Learning Hung-yi Lee 李宏毅.
Regularizing Face Verification Nets To Discrete-Valued Pain Regression
Part-Based Room Categorization for Household Service Robots
Deep learning and applications to Natural language processing
Training Techniques for Deep Neural Networks
Artificial Intelligence in Healthcare
Machine Learning: The Connectionist
Project Implementation for ITCS4122
ECE 599/692 – Deep Learning Lecture 6 – CNN: The Variants
State-of-the-art face recognition systems
FUNDAMENTALS OF MACHINE LEARNING AND DEEP LEARNING
Basic Intro Tutorial on Machine Learning and Data Mining
In summary C1={skin} C2={~skin} Given x=[R,G,B], is it skin or ~skin?
Layer-wise Performance Bottleneck Analysis of Deep Neural Networks
Computer Vision James Hays
Deep Face Recognition Omkar M. Parkhi Andrea Vedaldi Andrew Zisserman
Visual Question Generation
Introduction to Neural Networks
Neural network systems
Image Classification.
Towards Understanding the Invertibility of Convolutional Neural Networks Anna C. Gilbert1, Yi Zhang1, Kibok Lee1, Yuting Zhang1, Honglak Lee1,2 1University.
ECE 599/692 – Deep Learning Lecture 1 - Introduction
Introduction to Deep Learning with Keras
Very Deep Convolutional Networks for Large-Scale Image Recognition
Pose Estimation for non-cooperative Spacecraft Rendevous using CNN
Lecture: Deep Convolutional Neural Networks
Deep Learning for Non-Linear Control
Visualizing CNNs and Deeper Deep Architectures
John H.L. Hansen & Taufiq Al Babba Hasan
Ladislav Rampasek, Anna Goldenberg  Cell 
Heterogeneous convolutional neural networks for visual recognition
Course Recap and What’s Next?
Abnormally Detection
CSC 578 Neural Networks and Deep Learning
Natalie Lang Tomer Malach
CS295: Modern Systems: Application Case Study Neural Network Accelerator Sang-Woo Jun Spring 2019 Many slides adapted from Hyoukjun Kwon‘s Gatech “Designing.
VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION
Prabhas Chongstitvatana Chulalongkorn University
ICLR, 2019 Jiahe Li
Presentation transcript:

Deep Learning Tutorial Xudong Cao

Historical Line 1960s Perceptron 1980s MLP BP algorithm 2006 RBM unsupervised learning 2012 AlexNet ImageNet Comp. 2014 GoogleNet VGGNet ImageNet Comp. Big booming: DNNResearch 6M, DeepMind 400M Google, Microsoft, Baidu, FB, Apple Hundreds of Startups Rule based AI algorithm Game Tree & Search Algorithm Support vector machine Wrong direction

Linear inseparable problem & fitting power

Solution 1: Going High dimension Explicitly design high-dim. features e.g. high-dim LBP and fisher vector Implicitly project to high dim.

Solution 2: Going Deep

High-Dim VS. Deep High-Dim Deep Easy to train, convex in general Solid mathematic foundation Generalized well Low computational cost Fitting power scales linearly Hard to train, non-convex Black magic & unknown territory Prone to over-fitting High computational cost Fitting power scales exponentially

Explains why people hated neural networks in the past, BUT time changes …

New Era: Big Data & Moore’s Rule

Xiaogang Wang, Introduction to Deep Learning Practical application Xiaogang Wang, Introduction to Deep Learning

End-to-end learning, less domain knowledge Training Training Model Design Networks Design No or very small amount of domain knowledge Feature Design Conventional Approach Small amount of domain knowledge Deep Learning Pre-processing Large amount of domain knowledge Collect Data Collect Data

Xiaogang Wang, Introduction to Deep Learning Good features Xiaogang Wang, Introduction to Deep Learning

Good features cont. Transfer the face identification features to age estimation & gender classification Transfer ImageNet features to other tasks Dataset Conv. Best (acc) Tran. Best (acc) Oxford 102 Flowers 91.3% 98.7% Oxford-IIIT Pets 88.1% 93.1% FGVC-Aircraft 81.5% 85.2% MIT-67 indoor 49 68.9% 82.4% Human Age Estimation Dataset Pre. Best (MAE) Ours(MAE) Morph 3.6 2.4 FGNet 3.2 2.7 Geneder Classification Dataset Pre. Best (acc) Ours(acc) Morph 98.7% 99.4%

Directions of DL Research Feature engineering to architecture engineering ImageNet Classification with Deep Convolutional Neural Networks (Alex Net) Going Deeper with Convolutions (Google Net) Very Deep Convolutional Networks for Large-Scale Visual Recognition (VGG Net) Faster and smaller How to train very deep neural network Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (Speedup CNN training) Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification (Good initialization)

Directions of DL Research cont. Existing Applications Face: DeepFace, Deep ID serials & FaceNet Detection: R-CNN, fast R-CNN, faster R-CNN Segmentation: F-CNN serials New applications Image captioning [Google & Berkeley] Synthesize real world images [Facebook AI Lab] A Neural Algorithm of Artistic Style [Gatys et al.]