ml, machine learning, ml, python, artificial intelligence, ai, computer science, data science, data analytics, technology training at bay area, algorithm, deep learning, supervised learning, unsupervised learning, database, logistic regression, polynomial regression, rnns
CSE590/MB590 Special Topics
  - Computer Vision,Deep Learning and AI

This course introduces students Artificial Intelligence, Deep Learning that relates to Computer vision. This course is designed to enhance your existing machine learning and deep learning skills with the addition of computer vision theory and programming techniques.
  • » 23 hours (8 weeks) in class lecturing plus dedicated mentoring sessions from our faculty of industry experts
  • » 1.5 semester credits for both certificate and master’s degree
  • » Access to high-quality live class recording
  • » Online live classroom available for all classes
  • » Lifetime learning resources for our students
  • ETTP Program $7200
Course Description

This course introduces students Artificial Intelligence, Deep Learning that relates to Computer vision. This course is designed to enhance your existing machine learning and deep learning skills with the addition of computer vision theory and programming techniques. These computer vision skills can be applied to various applications such as image and video processing, autonomous vehicle navigation, medical diagnostics, smartphone apps, and much more. This program will not prepare you for a specific career or role, rather, it will grow your deep learning and computer vision expertise and give you the skills you need to start applying computer vision techniques to real-world challenges and applications. Building a projects is one of the best ways to demonstrate the skills you’ve learned and each project will contribute to an impressive professional portfolio that shows potential employers your mastery of computer vision and deep learning techniques.

Prerequisite: Programming experience with python, basic understanding of command line.

Measurable Course Objectives
  • The goal of this course is to give learners basic understanding of modern neural networks and their applications in computer vision and natural language understanding.
  • Implement common deep learning workflows such as Image Classification and Object Detection.
  • Experiment with data, training parameters, network structure, and other strategies to increase performance and capability.
  • Deploy your networks to start solving real-world problems.
  • Be familiar with fundamental concepts and applications in computer vision
  • Grasp the principles of state-of-the art deep neural networks
  • Understand low-level image processing methods such as filtering and edge detection
  • Gain knowledge of high-level vision tasks such as object recognition, scene recognition, face detection and human motion categorization
  • Develop practical skills necessary to build highly accurate, advanced computer vision applications
University-wide Student Learning Outcome

The University Student Learning Outcomes assessed and reinforced in this course include but are not limited to the following:

  • Communication
  • Critical Thinking
  • Information Literacy
Course Topics
Week 1:Introduction and Overview:
  • Course Overview and Motivation; Introduction to Image Formation, Capture and Representation; Linear Filtering, Correlation,Convolution
Week 2: Visual Features and Representations and Visual matching:
  • Edge, Blobs, Corner Detection; Scale Space and Scale Selection; SIFT, SURF; HoG, LBP, Bag-of-words, VLAD; RANSAC, Hough transform; Pyramid Matching; Optical Flow
Week 4:Deep Learning Review and Convolutional Neural Networks (CNNs):
  • Review of Deep Learning, Multi-layer Perceptrons, Backpropagation, Introduction to CNNs; Evolution of CNN Architectures: AlexNet, ZFNet, VGG, InceptionNets, ResNets, DenseNets
Week 5: Neural Networks Architecture Hyperparameter tuning:
  • Review Neural Network Architecture and hyperparameter tuning for Deep Learning: Neural network types, type of layers, weight initialization, activation function, regularization, learning rate, momentum, decay rate, fitness, epochs, optimization, back propagation, different pre-trained networks, training methods.
Week 6:Visualization and Understanding CNNs:
  • Visualization of Kernels; Backprop-to-image/Deconvolution Methods; Deep Dream, Hallucination, Neural Style Transfer; CAM,Grad-CAM, Grad-CAM++; Recent Methods (IG, Segment-IG, SmoothGrad)
Week 7:CNNs for Recognition, Verification, Detection, Segmentation:
  • CNNs for Recognition and Verification (Siamese Networks, Triplet Loss, Contrastive Loss, Ranking Loss); CNNs for Detection: Background of Object Detection, R-CNN, Fast R-CNN, Faster R-CNN, YOLO, SSD, RetinaNet; CNNs for Segmentation: FCN, SegNet, U-Net, Mask-RCNN
Week 8:Recurrent Neural Networks (RNNs), Face detection, generative models and application of Generative models
  • Review of RNNs; CNN + RNN Models for Video Understanding: Spatio-temporal Models, Action/Activity Recognition, Review of (Popular) Deep Generative Models: GANs, VAEs; Other Generative Models: PixelRNNs, NADE, Normalizing Flows, etc. Applications: Image Editing, Inpainting, Superresolution, 3D Object Generation, Security; Variants: CycleGANs, Progressive GANs, StackGANs, Pix2Pix, etc
Misc: Recent Trends:
  • Zero-shot, One-shot, Few-shot Learning; Self-supervised Learning; Reinforcement Learning in Vision; Other Recent Topics and Applications
About the Instructor

Bhairav Mehta

Bhairav Mehta is Data Science Manager at Apple Inc. Senior Data Scientist and Technical Program Manager with 14 years experience in Analytics, Data Science, AI/ML, Big-Data and Program management at Fortune 10 companies (Apple, Qualcomm, Ford) and startups (MIT Startup) in various industry verticals. Focused, highly dependable and detail-oriented solutions architect offering exceptional problem solving, troubleshooting skills and a talent for developing innovative solutions to unusual and difficult problems. Demonstrated performance in leading high performance teams in delivery of actionable solutions to business problems. Extensive education with 5 masters degrees in engineering, statistics (Cornell), computer science (GeorgiaTech) and MBA (Cornell) from Ivy league University. US Citizen (Naturalized)