Deep Neural Network

      Statistics Base

      Continuous, Discrete & Categorical Data

      Shape of The Data & Distribution Analysis

      Anova

      Advanced Statistics

      Visualization In Python I: MatplotLib

      Visualization In Python II: Seaborn

      Advanced Visualization in Python

      Unclean Data

      Issues with Data

      Data from Multiple sources

      Data Cleaning I: Normalization

      Data Cleaning II: Missing Values, Outliers

      Preparing data for Machine Learning:

      Comparison of Results with Clean & Unclean data for

      MultiLinear Regression

      Machine Learning Intro: Supervised, Unsupervised & Semi

      Train, test: Model creation & Prediction Demo

1. Supervised Learning Intro:

a. Classification & Regression

2. Regression Analysis

3. Linear Regression

4. SciKit Learn Intro

5. First ML Program: Linear Regression

a. Multi Linear Regression

b. Polynomial Regression

c. Linear Regression Deep dive: Internal Working

d. Cost Function: Gradient Descent

e. Convergence

f. Trouble shooting Non-Convergence

6. Trouble shooting Accuracy of Model performance:

a. Calculating the Error

b. Underfitting: High Bias

c. Overfitting: High Variance

d. Resolving Issues with Accuracy: Regularization

7. Advanced Polynomial Regression

8. Realtime Project on Regression

9. Classification Introduction

a. Calculating Accuracy In Classification

10. Logistic Regression

a. Logistic Regression: Working & Cost Function

b. Logistic Regression for Classification Project

11. Additional ML Algorithms for Regression:

a. Decision Trees

i. Regression

ii. Classification

b. Ensemble Learning: Random Forrest

i. Regression

ii. Classification

c. Support Vector Machines: Basics & Cost Function, Wide Margin Classifier

i. Support Vector Regression

ii. Support Vector Classifier

iii. Kernel SVM: Linear Kernel

iv. Gaussian Kernel

d. Naive Bayes

e. KNN(K Nearest Neighbours)

f. Naive Bayes MNIST

g. Advanced Naive Bayes: Working with Text data and Text based Classification

12. Advanced Machine Learning Concepts

a. KFold Cross Validation

Feature Selection & Feature Engineering

      Model Persistance, Evaluation, Retraining

      Ensemble Learning with Multiple ML Algorithms

      Bagging to Improve Accuracy

      Boosting to Improve Accuracy

      Gradient Boosting

      AdaBoost(Ensemble Learning): Weigthts

      Upper Confidence Bound(UCB) & Thomson Sampling

      ML As a Service(ML Web Service)

1. Clustering

a. KMeans Clustering

b. Hierarchical Clustering: Agglomerative & Devisive

c. Dendo Grams, Hierarchical Trees

2. Dimensionality Reduction: Projections

a. Principal Component Analysis(PCA)

b. Kernel PCA

c. Supervised Dimensionality Reduction: LDANoSQL:

3. Association Rule Mining

a. Apriori or Market Basket Analysis

Structured & Semistructured Data
MongoDB for Document Store DB
NoSQL Databases Role in Machine Learning: MongoDB

1. Advanced Machine Learning:

2. Neural Networks Intro

a. Artificial Neural Networks(ANN)

b. Deep Neural Networks

c. Convolutional Neural Networks(CNN)

d. Recurrent Neural Networks(RNN)

e. Stock Price Prediction using Neural Networks: Demo

f. Neural Net Concepts:

g. Neurons as Nodes: Perceptrons

h. Dense & Sparse Neural Networks

3. Neuron Based approach: Benefits

a. Perceptrons

b. Learning Weights

c. Gradient Descent & Back Propagation

d. Activation Function & Feedforward Neural Networks

4. Installing Prerequisite Softwares:

a. Tensorflow

b. Theano

c. Keras

5. 3 Layer Neural Network for Customer Churn Modeling

6. Online Learning(Reinforcement Learning)

7. Generalized Aditive Modeling(GANS)

8. PyTorch

9. Image Processing Introduction

a. OpenCV for Image Processing in Python

b. Edge Detection

c. Eye & Nose Detection

d. Face Detection using Haar cascades

e. Optical Character Recognition using Neural Networks

f. Text Detection: Sliding Window

g. Character Segmentation

h. Character Classification

10. Synthetic Character Generation: Shearing & Scaling, Rotation

11. Revisiting Perceptrons

a. Coding a Text Classifier in Neural Networks

12. Advanced Neural Nets:

13. Long Short Term Memory(LSTM) in RNN

14. Time Series Data(ARMA, ARIMA)

15. Unsupervised Learning using Hidden Markov Model(Tensorflow and Theano)

16. Tensorflow Deep Dive

17. Speech Recognition

18. Advanced Text Mining

19. Building & Deploying a Intelligent Chatbot

a. Data Preprocessing

b. Seq2Seq

c. Deploying the Chat Application

20. Computer Vision as AI

21. Image Recoginition and Classification

22. Deep Neural Networks Architecture revisited

23. Deep Convolutional Neural Network for Image Recognition:

a. Convolutions

b. Pooling, Flattening

c. LeNet, Fully Connectected Feed Forward Network

d. Face Recognition using Convolutional Neural Network

e. Importing Pretrained Models

f. Running Convolutional Neural Networks on GPU for Image

24. Unsupervised Learning in Deep Neural Networks Revisited

a. Current Advancements:

i. Self Organizing Maps(SOM)

ii. Auto Encoders

iii. Boltzman Machines

25. VGG, SDD, ResNet

26. Future Direction: Self Driving Cars, IIoT with AI, Drone based Parcel Delivery, etc

27. Conclusion