Description

Data Science is most lucrative careers with unlimited opportunity today!! Data Science career requires key Data Engineering and Machine Learning, Artificial Intelligence and Deep Learning skills to be successful. This training will teach you all skills needed to be a successful Data Scientist. Its not only algorithms or tools but an end to end skills needed with latest advancements in the industry today. Project and Learning by examples is at core of this training. 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 new AI problems you might encounter in life.

Schedule:

Day 1

Overview and Introduction

Data Science Introduction

Data Infrastructure Introduction

Distributed and In-memory computing

Hadoop Distributed File System and Spark In-Memory computing. RDDs, HDFS, Commodity Cloud Infrastructure

Hadoop and Spark Labs on Cloud

Rest APIs and Data pipelines

Data Formats JSON, BSON, XML data structures, Data pipelines and parsing routines in Python

Machine Learning Introduction

Unsupervised and Supervised algorithms introduction

Unsupervised algorithms: Clustering, Discriminant Analysis, Dimensionaility Reduction techniques like PCA/ LDA/FA/ DA

Supervised algorithms: Classifiers, Regression, Ensemble algorithms like Random Forest

Diagnostic tools for evaluating models: ROC Curves, Lift Curve, Bias Variance Tradeoffs, F1 scores etc.

Machine Learning Labs with Python on GPU/TPU Cloud @ Google Colab and/or Kaggle Kernels

Building Machine Learning algorithm deployment at Scale using state of the art Cloud based tools.

AI ML Hardware Acceleration using GPU, TPU and FPGA

Data Science Pipelines with Big data and Cloud based tools for storage and compute

Neural Network Introduction

Gradient Descent, Error function

Training Neural Network

Tensorflow, Keras, Theano, Lasagne, Torch, Caffe introduction

Tensorflow Labs

Day 2

Tensorflow and Keras labs for simple classification and clustering. Supervised and unsupervised.

Regularization Intro

Neural Network Architecture and Hyper Parameter tuning

Convolution Neural Network

Labs with Tensorflow and CNN, CNN with Regularization

CNN in Tensorflow

Weight Initialization

Auto Encoders

Transfer Learning

ImageNet, LeNet, Alexnet, VGGNet, Inception, ResNet

Object Detection

Auto Encoder and Transfer learning labs

Image Segmentation

Face Detection

Image Classification

Labs with Keras and TensorFlow

Advanced Object Detection methods: R-CNN, F R-CNN, YOLO, Mask R-CNN, Labs

Labs for Image Classification

Labs for Image Segmentation and Face detection

Recurrent Neural Network Intro (RNN)

Long Short term Memory (LSTM)

Motivation for learning RNN and LSTM

Simple RNN and LSTM labs for Time Series

Cloud based tools for doing object detection, image classification and applications of CNN

RNN-LSTM Labs continued

Natural Language Processing (NLP)

Work2Vec, Word Embedding, PCA and T-SNE for Word Embedding

NLP Labs

Sequence to Sequence LSTM Chatbots and LSTM based Text Generation

Review and Introduction to advanced concepts in Neural Networks e.g. Reinforcement Learning, Generative Adversarial Networks, Autonomous Driving car etc.

Intended Audience

Programmers, analysts, managers, investors, enthusiast pretty much anyone technically curious about deploying Machine Learning.

TextBooks and Slides:

Slides (To be delivered separately)

Following material will be provided by Bhairav Mehta (It is worth USD300.00)

12 workshop guides will be provided

Machine Learning Algorithms
Deep Learning and Python CNN
Deep Learning and Natural Langugage Processing
LSTM and RNN
Machine Learning with Python
Big Data tools Distributed and In Memory computing
Additional Books are on specific topics in AI / ML and Big Data. Each topic includes codes and explanation step-by-step