[Special Session on 26 July, 2018] [★]Develop and Deploy Deep Learning Based Vision Applications Using Matlab - Dr. Rishu Gupta (Mathworks Representative)

Program Schedule

[Note] The lecture session will be held in #5055, CC-3 (Ground Floor) and Lab Session to take place in Computer Vision & Biometrics Lab, #5322, CC-3 (Third Floor).

Date/Time 14 July 15 July 16 July 17 July 18 July 19 July
0800-0845 Breakfast
0900-1000 Registration Ensemble Learning
- Dr. Partha Pratim Roy		 Bias variance Problem: Generalization & Regularization
- Dr. Balasubramanian Raman		 Deep dictionary learning - a new deep learning framework
- Dr. Angshul Majumdar 		Back Propagation, Chain Rule, Gradient Descent
- Dr. Shekhar Verma		 Optimization Techniques Contd.: Gradient Descent, SGD, MSGD, Chain Rule etc
- Dr. Krishna Pratap Singh
1000-1100 Inauguration/KeyNote Talk -
Prof. P. Nagabhushan (Director IIITA)		 Ensemble Learning
- Dr. Partha Pratim Roy		 Bias variance Problem: Generalization & Regularization
- Dr. Balasubramanian Raman		 Deep dictionary learning - a new deep learning framework
- Dr. Angshul Majumdar		 Back Propagation, Chain Rule, Gradient Descent
- Dr. Shekhar Verma		 Optimization Techniques Contd.: Gradient Descent, SGD, MSGD, Chain Rule etc
- Dr. Krishna Pratap Singh
1100-1130 Tea Break
1130-1230 Machine Learning Techniques
- Dr. Bidyut Baran Chaudhuri 		Mathematical aspects of Machine Learning
- Dr. Balasubramanian Raman 		Cross-Language Framework for Low-Resource Handwritten Image Analysis
- Dr. Partha Pratim Roy		 Neural network Architecture: Perceptron, Neural Networks, Multilayer Neural networks
- Dr. Shekhar Verma		 Optimization Techniques in Deep Architecture
- Dr. Krishna Pratap Singh		 CNN: Convolution Layer, Non Linear Layer, Pooling Layer, Fully Connected Layer, Classification Layer, Progress on ImageNet Challenge
Dr. Shiv Ram Dubey
1230-1430 Lunch Break
1430-1530 Pre Deep Learning Classification architecture on Principle Component Analysis, Nearest Neighbor, K- Nearest Neighbor & Linear Classifier
- Dr. Bidyut Baran Chaudhuri		 PyTorch & Tensorflow Basics
- Dipti Mishra & Nayaneesh Mishra		 Introduction to Matlab
- Sumit Kumar		 Triveni Sangam Visit 3D Deep Architecture & Activity Recognition
- Nayaneesh Mishra 		Voluntary Assessment I
1530-1630 Getting Started with Python3 (Practical)
- Albert Mundu		 PyTorch & Tensorflow Basics
- Dipti Mishra & Nayaneesh Mishra		 Introduction to Matlab
- Sumit Kumar		 Triveni Sangam Visit 3D Deep Architecture & Activity Recognition
- Nayaneesh Mishra 		Voluntary Assessment I
1630-1700 Tea Break
1700-1800 Getting Started with Python3 (Practical)
- Albert Mundu		 PyTorch & Tensorflow Basics
- Dipti Mishra & Nayaneesh Mishra		 Introduction to Matlab
- Sumit Kumar		 Triveni Sangam Visit 3D Deep Architecture & Activity Recognition
- Nayaneesh Mishra 		Voluntary Assessment I


>
Date/Time 20 July 21 July 22 July 23 July 24 July 25 July
0800-0845 Breakfast
0900-1000 Training Aspects of CNN-I
- Dr. Shiv Ram Dubey		 Fleet Management: The Sexiest Problem in Data Science
- Dr. Gaurav Aggarwal		 GoogLeNet , ResNet, Pre-activated ResNet, Squeeze and Excitation Network (SENet), Deep Network with Stochastic Depth, DenseNet, ResNeXt
- Dr. Shiv Ram Dubey		 Object Detection I
- Akhilesh Kumar		 ABB and Machine learning prospects on Industrial robots II
- Mohak Sukhwani		 Wearable Cameras: A New Camera Point of View - I
- Dr. Chetan Arora
1000-1100 Training Aspects of CNN-I
- Dr. Shiv Ram Dubey		 Fleet Management: The Sexiest Problem in Data Science
- Dr. Gaurav Aggarwal		 GoogLeNet , ResNet, Pre-activated ResNet, Squeeze and Excitation Network (SENet), Deep Network with Stochastic Depth, DenseNet, ResNeXt
- Dr. Shiv Ram Dubey		 Object Detection I
- Akhilesh Kumar		 Object Detection II
- Akhilesh Kumar		 Wearable Cameras: A New Camera Point of View - II
- Dr. Chetan Arora
1100-1130 Tea Break
1130-1230 Variational Autoencoders, RNN,LSTM
- Prof. Shekhar Verma 		LeNet, AlexNet, ZFNet, VGGNet, Network in Network
- Dr. Shiv Ram Dubey		 ABB and Machine learning prospects on Industrial robots I -
Mohak Sukhwani		 [Lab] Deep Generative Adversarial Network
- Suranjan Goswami		 Object Detection II
- Akhilesh Kumar		 Wearable Cameras: A New Camera Point of View - III
- Dr. Chetan Arora
1230-1430 Lunch Break
1430-1530 Training Aspects of CNN-II
- Dr. Shiv Ram Dubey		 Lab Discusson Hands on with Auto Encoders, RNN etc.
- Mohak Sukhwani		 City Visit Reinforcement Learning
- Suvidha Tripathi		 Video Based Facial features
- Nayaneesh Mishra
1530-1630 Training Aspects of CNN-II
- Dr. Shiv Ram Dubey		 Lab Discusson Hands on with Auto Encoders, RNN etc.
- Mohak Sukhwani		 City Visit Reinforcement Learning
- Suvidha Tripathi		 Video Based Facial features
- Nayaneesh Mishra
1630-1700 Tea Break
1700-1800 Keynote Talk
- Padmashree Prof. S. K. Pal		 --- Hands on with Auto Encoders, RNN etc.
- Mohak Sukhwani		 City Visit Reinforcement Learning
- Suvidha Tripathi		 Video Based Facial features
- Nayaneesh Mishra


Date/Time 26 July 27 July 28 July
0800-0845 Breakfast
0900-1000 RNN & LSTM
- Dr. Venkatesh Babu		 Deep Generative Models I: GAN, Conditional GAN, Recent Developments (Star GAN, Disco GAN, Progressive GAN)
- Dr. Vineeth NB		 Terahertz Imaging & Communication
- Dr. Mukesh Jewariya
1000-1100 RNN & LSTM
- Dr. Venkatesh Babu		 Deep Generative Models I: GAN, Conditional GAN, Recent Developments (Star GAN, Disco GAN, Progressive GAN)
- Dr. Vineeth NB		 Terahertz Imaging & Communication
- Dr. Mukesh Jewariya
1100-1130 Tea Break
1130-1230 --- Deep Generative Models II: Variational Autoencoders
- Dr. Vineeth NB		 Critics on Deep Learning
- Uma Shankar Tiwary
1230-1430 Lunch Break
1430-1530 [★]Develop and Deploy Deep Learning Based Vision Applications Using Matlab
- Dr. Rishu Gupta (Mathworks Representative)		 Voluntary Assessment II Poster Session
1530-1630 [★]Develop and Deploy Deep Learning Based Vision Applications Using Matlab
- Dr. Rishu Gupta (Mathworks Representative)		 Voluntary Assessment II Distribution
1630-1700 Tea Break
1700-1800 [★]Develop and Deploy Deep Learning Based Vision Applications Using Matlab
- Dr. Rishu Gupta (Mathworks Representative)		 --- Snacks & Group Photo

[★]Develop and Deploy Deep Learning Based Vision Applications Using Matlab - Dr. Rishu Gupta (Mathworks Representative)

ABSTRACT
Designing and deploying deep learning based computer vision applications to embedded CPU and GPU platforms is challenging because of resource constraints inherent in embedded devices. A MATLAB® based workflow facilitates the design of these applications, and automatically generated C or CUDA® code can be deployed on boards like the Jetson TX2 and DRIVE™ PX to achieve very fast inference. The workshop illustrates how MATLAB supports all major phases of this workflow. Starting with algorithm design, the algorithm may employ deep neural networks augmented with traditional computer vision techniques and can be tested and verified within MATLAB. Next, these networks are trained using GPU and parallel computing support for MATLAB either on the desktop, cluster, or the cloud. Finally, GPU Coder™ generates portable and optimized C/C++ and/or CUDA® code from the MATLAB algorithm, which is then cross-compiled and deployed to ARM/Intel CPUs and NVIDIA Tegra® boards.

HIGHLIGHTS

  • Introduction to Deep Learning for Computer Vision Applications Using MATLAB
  • Use a pretrained network for image classification
  • Build a deep learning network from scratch
  • Perform transfer learning

Addressing Challenges in Deep Learning Workflows Using MATLAB

  • Accelerating the labelling process using automation algorithms
  • Hyperparameter tuning of deep neural networks
  • Scaling up training to GPUs, multi-GPUs and clusters
  • Deployment workflows for desktop, web, and cloud
  • Automatic code generation and deployment for embedded platforms (NVIDIA GPU, Intel CPU, ARM CPU)