Duration
5 days
Course Structure
This course focuses on the practical aspects of Machine Learning, Deep Learning and Artificial Intelligence. The objective is to make use of TensorFlow for various types of neural networks. The participants will build and train deep learning models.
Intended Audience
The intended audience for this course:
- Data Engineers
- Data Scientists
- Machine Learning Engineers
- Integration Engineers
- Architects
Prerequisites and Lab details:
Participants should preferably have some experience with Python.
Course Outline
Understanding the Big Picture
- Artificial Intelligence (AI) Overview
- What is Machine Learning (ML)?
- AI vs ML vs Data Science
- Relationship between Deep Learning (DL) and Machine Learning
- Practical Use cases
- Concepts and Terms
- Tools/Platforms for ML, DL and AI
- Machine Learning Project End to End Pipeline
- Scalable ML/AI: Big Data and Cloud fits into the Ecosystem
GCP Introduction
- GCP Introduction.
- Why Google Cloud Platform (GCP)?
- How Innovations at Google driving Data Engineering and Science globally?
- Key Google Products related to Data and Machine Learning
- Come on same page w.r.t. terms and concepts
Getting holistic view: Architectures and Pipelines
- Introduction to Serverless Architecture
- Current Challenges with On-Premise Architectures
- How Google enables higher productivity?
- How Key Google Products fit in Enterprise Architecture?
- How to design modern Data Analytics Pipeline on GCP?
Machine Learning APIs
- Introduction to Machine Learning APIs
- Key ML Use Cases
- Vision API
- Natural Language API
- Translate API
- Speech API
Environment for Experiments
- Installing Anaconda
- Setting up Jupyter Notebook
- Experiencing Notebooks
- Key Python Syntax Recap
- Hands-on Exercises
Key Statistics
- Summary Statistics
- Exploratory Analysis
- Numerical Computation using Python
- Hands-on Exercises
Data Visualization
Overview
- Using MatPlot Lib
- Key types of plots
- Exploratory Analysis using MatPlot Lob
- Hands-on Exercises
Acquiring & Preparing Data
- Content Acquisition Approaches, Pros & Cons
- Working with Beautiful Soup
- Acquiring data using Rest Based APIs
- Data Cleaning & Wrangling using Pandas
- Missing Values and Outlier
- Hands-on Exercises
Feature Engineering
- What is Feature Engineering?
- Why Feature Engineering?
- How to apply Feature Engineering?
- Discussions on various scenarios
- Hands-on Exercises
Machine Learning using Scikit Learn
- Types of Machine Learning
- Key Algorithms in Machine Learning
- Practical Applications of Machine Learning
- Various frameworks/Libraries popular for ML
- Concepts and Terms
- Why Scikit Learn?
- Code Walkthrough
- Hands-on Exercises
Supervised Machine Learning
- Key Classification Algorithms
- Naïve Bayes Classifier
- Confusion Matrix
- Accuracy
- Key Regression Algorithms
- Linear, Logistic Regressions
- Gradient Descent
- Loss function
- Bias vs Variance Tradeoff
- Evaluating Models
- Hands-on Exercises
Un-Supervised Machine Learning
- Principal Component Analysis
- Performing Clustering of data
- Using Collaborative filtering for Recommendations
- Hands-on Exercises
Spark Introduction
Overview
- Understand What is Spark
- Describe RDDs
- Explain Spark Components
Spark SQL
Introduction
- Using the SQL API – sqlContext.sql
- Dataframe API
- Working with various Datasources
- Inferred Schemas
- Querying DataFrames Using Column Expressions
Spark Machine Learning
- Quick introduction to Machine Learning
- Introduction to ML and MLLib Spark
- Data types - Vectors, Matrices, LabeledPoint
- Summary Statistics
- Calculating Correlations
- Creating Vectors from Dataframe
- Transformers, Estimators and Pipelines
- Evaluation of Model
- Walkthrough of a Regression model
- Walkthrough of a K Means Clustering model
- Hands-on on Working with Machine Learning Pipelines
Introduction to Deep Learning
- What is Deep Learning?
- Relationship between Deep Learning and Machine Learning
- Deep Learning Use cases
- Concepts and Terms
- How to implement Deep Learning?
- Hands-on: Recap on Machine Learning
Artificial Neural Network
- Introduction to Neural Networks
- Introduction to Perceptron
- Neural Network Activation Functions
- Basic Neural Nets
- Concepts
TensorFlow API
- What is TensorFlow?
- Installing TensorFlow
- TensorFlow Graphs
- Variables and Placeholders
- Linear Regression
- Nonlinear Regression
- Logistic Regression
- Activation Functions
Convolutional Neural Networks (CNN)
- CNN History
- Understanding CNNs
- CNN Application
Recurrent Neural Networks (RNN)
- Intro to RNN Model
- Long Short-Term memory (LSTM)
- Recursive Neural Tensor Network Theory
- Recurrent Neural Network Model
Interactive Data exploration using DataLab
- Spinning up Cloud DataLab
- Experiencing Datalab notebooks
- Exploring Google Cloud Storage
- Leveraging relational data with Google Cloud SQL
- Reading and writing streaming Data with Google BigTable
- Querying Data from Google BigQuery
- Making Google API Calls from notebooks
CloudML: Scalable Models on GCP
- Why Cloud ML?
- Running TensorFlow model in Local mode
- Porting TensorFlow models to GCP
- Deploying Models in Production
- Model Predictions
- Hands-on exercise(s)
Conversational AI
- Intro to ChatBots
- Key options available
- Building ChatBot
- Hands-on Exercise using DialogFlow API
Programme scope, delivery arrangements and suitability are confirmed during enquiry.