Title:Serverless Machine Learning with TensorFlow
Date:9:00am-4:30pm, 1/25, Friday
Instructor:Chris Rawles, Google
Chris is a ML Solutions Engineer in Google Cloud where he teaches ML to Google customers and builds ML models using TensorFlow and Google Cloud. In his past work as a researcher, Chris used machine learning to study earthquakes.
Course Outline:
9-10am: Module 1: Identify use cases for machine learning
10-11am: Module 2: Explore a dataset, create ML datasets, and create a benchmark
11-12pm: Module 3: Getting started with TensorFlow
  • Use of tf.estimator
  • Dealing with input data
  • Performing feature engineering
  • Building and training models
  • Lab
12-1:30pm: Lunch break
1:30-2:30pm: Module 4: Distributed training and monitoring
2:30-3:00pm: Module 5: Productionize trained ML models, and scale up ML
3:00-4:00pm: Module 6: Advanced feature engineering and combining features
4:00-4:30pm: Module 7: Hyper-Parameter tuning
Who should learn:Developers, Data Scientists who are working on machine learning, deep learning.
Level:Beginner to Intermediate
Prerequsite:The following is prefered but not required.
  • Experience using Python
  • Basic proficiency with a common query language such as SQL
  • A working knowledge of data modeling and extract, transform, load activities
  • Basic familiarity with machine learning and/or statistics
Back to Home
Title:Accelerating AI through Automated Machine Learning
Date:9am-12pm, 1/25, Friday
Instructor:Sujatha Sagiraju, Microsoft
Course Outline: As a data scientist, for a given machine learning problem, you run multiple ML models to find the right model. For example, for a machine learning classification problem, you could be running your data through many different classifiers available such as SVM, Logistic Regression, Boosted Decision Tress etc. In addition, you are also trying many different hyper parameters such as learning rate, depth of the tree etc. There is no way to find out which model & hyper parameters is best other than trying out many different combinations manually. That is lot of training jobs and manual tuning before you find an optimal model that gives you the performance characteristics that you are satisfied with. AutoML uses intelligent optimization techniques to build a high quality model and does so by providing a simple interface to the user. It is just one method call.
9-10am: Module 1: Intro and overview
10-12pm: Module 2: Code lab
  • Installation and Configurtion
  • Using Azure ML
  • Inspect and Experience Models
  • Deploy Models
Who should learn:Data scientists, Developers, BI professionals, Analysts
Level:Beginner to Intermediate
Prerequsite:
Back to Home
Title:Deep Learning in Action
Date:9:00am-4:30pm, 1/26-27(Sat, Sun)
Instructor:Bhairav Mehta, Sr. Data Scientist, Apple
He has 15 years experience in Analytics and Data Science space at various fortune 100 companies. Bhairav Mehta is academician and tenured faculty at various Bay area Universities. Bhairav Mehta has taught 1000s of students in AI, ML and Big Data technologies over last 5 years. He also gives talks at Association of Computing Machinery (ACM), IEEE Computer Science society, and various AI Conferences. Bhairav Mehta has 5 graduate degrees from top institutes: MS Computer Science (GeorgiaTech), MBA (Cornell University), MS Statistics (Cornell University)
Course Objectives:What do web search, speech recognition, face recognition, machine translation, autonomous driving, and automatic scheduling have in common? These are all complex real-world problems, and the goal of artificial intelligence (AI) is to tackle these with rigorous mathematical tools. In this course, you will learn the foundational principles that drive these applications and practice implementing some of these systems. Specific topics include machine learning, search, game playing, Markov decision processes, constraint satisfaction, graphical models, and logic. The main goal of the course is to equip you with the tools to tackle AI problems.
Course Include:
  • 2 days/12 hours instructor-led trainings
  • 10 modules of lectures
  • 8 hands-on code labs
  • Code labs guidance
  • Training materials
Course Outline:
Day 1:
9-10am: Module 1: Overview and Introduction
  • Overview and Introduction
  • Introduction to Neural Networks
  • Current /Future Industry Trends
  • Your First Neural Network
  • Lab 1: Google Colab Cloud Platform Intro and Set up
10-11am: Module 2: Get Started on Machine Learning
  • Introduction
  • Gradient Descent, Error function
  • Training Neural Network
  • Supervised and unsupervised
  • Tensorflow, Keras, Theano, Lasagne, Torch, Caffe introduction
  • Lab 2: Tensorflow and Keras labs for classification and clustering
11-12pm: Module 3: Neural Networks
  • Regularization Intro
  • Neural Network Architecture and Hyper Parameter tuning
  • Convolution Neural Network
  • Lab 3: Tensorflow and CNN, CNN with Regularization
12-1:30pm: Lunch break
1:30-3:00pm: Module 4: More on Neural Networks
  • CNN in Tensorflow
  • Weight Initialization
  • Auto Encoders
  • Transfer Learning
  • ImageNet, LeNet, Alexnet, VGGNet, Inception, ResNet
  • Object Detection
  • Lab 4: Auto Encoder and Transfer learning
3:00-4:30pm: Module 5: Object Detection
  • Image Segmentation
  • Face Detection
  • Image Classification
  • Lab5: Keras and TensorFlow
Day 2
9-11am: Module 6: Advanced Object Detection
  • R-CNN, F R-CNN, YOLO, Mask R-CNN
  • Lab6: Image Classification
  • Lab7: Image Segmentation and Face detection
11-12pm: Module 7: Advanced Neural Networks
  • Recurrent Neural Network Intro (RNN)
  • Long Short term Memory (LSTM)
  • Motivation for learning RNN and LSTM
  • Lab 8: RNN and LSTM labs for Time Series
  • Cloud based tools for doing object detection, image classification and applications of CNN
12-1:30pm: Lunch break
1:30-2:30pm: Module 8: Labs
  • Lab 9: RNN-LSTM Labs continued
2:30-3:30pm: Module 9: Natural Language Processing
  • Sequence to Sequence LSTM Chatbots and LSTM based Text Generation
  • Natural Language Processing (NLP)
  • Work2Vec, Word Embedding, PCA and T-SNE for Word Embedding
  • Lab 10: NLP Labs
3:30-4:30pm: Module 10: Summary and Next steps
  • Review and Introduction to advanced concepts
  • Reinforcement Learning
  • Generative Adversarial Networks
  • Autonomous Driving car
Who should learn:Developers, Data Scientists who are working on machine learning, deep learning.
Level:Beginner to Intermediate
Prerequsite:
Back to Home