Training

Deep Learning Master

Course Syllabus

Python Basics:
  • Introduction to Data Science
  • Python Intro: Anaconda, Pip for package management, Virtual Env for isolation
  • Python Advanced Data Structures I: Numpy
  • Python Advanced Data Structures II: Pandas
  • Python Database Connectivity
  • Python Data Parsing:
    • Request to download data
    • Parse HTML
    • Parse JSON
    • Parse XML
    • Web Scrapping Basics
  • Regular Expressions
  • Natural Language Processing Intro
  • Python NLP using NLTK
  • Advanced NLTK: Sentiment Analysis techniques
  • Advanced Web scrapping & NLTK: Auto News Article Summarizer
Statistics
  • Statistics Base
  • Continuous, Discrete & Categorical Data
  • Shape of The Data & Distribution Analysis
  • Anova
  • Advanced Statistics
Visualization
  • Visualization In Python I: MatplotLib
  • Visualization In Python II: Seaborn
  • Advanced Visualization in Python
Exploratory Data Analysis
  • Unclean Data
  • Issues with Data
  • Data from Multiple sources
Extract Transform & Load (ETL)
  • 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
  • Machine Learning Intro: Supervised, Unsupervised & Semi
  • Train, test: Model creation & Prediction Demo
Supervised Learning Algorithms
  • Supervised Learning Intro:
    • Classification & Regression
  • Regression Analysis
  • Linear Regression
  • SciKit Learn Intro
  • First ML Program: Linear Regression:
    • Multi Linear Regression
    • Polynomial Regression
    • Linear Regression Deep dive: Internal Working
    • Cost Function: Gradient Descent
    • Convergence
    • Trouble shooting Non-Convergence
  • Trouble shooting Accuracy of Model performance:
    • Calculating the Error
    • Underfitting: High Bias
    • Overfitting: High Variance
    • Resolving Issues with Accuracy: Regularization
  • Advanced Polynomial Regression
  • Realtime Project on Regression
  • Classification Introduction:
    • Calculating Accuracy In Classification
  • Logistic Regression:
    • Logistic Regression: Working & Cost Function
    • Logistic Regression for Classification Project
  • Additional ML Algorithms for Regression:
    • Decision Trees
      • Regression
      • Classification
    • Ensemble Learning: Random Forrest
      • Regression
      • Classification
    • Support Vector Machines: Basics & Cost Function, Wide Margin Classifier
      • Support Vector Regression
      • Support Vector Classifier
      • Kernel SVM: Linear Kernel
      • Gaussian Kernel
    • Naive Bayes
    • KNN(K Nearest Neighbours)
    • Naive Bayes MNIST
    • Advanced Naive Bayes: Working with Text data and Text based Classification
  • Advanced Machine Learning Concepts
    • KFold Cross Validation
Advanced Machine Learning
  • 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)
    • a. Binary Classifier as a Service
Unsupervised Machine Learning
  • Clustering
    • KMeans Clustering
    • Hierarchical Clustering: Agglomerative & Devisive
    • Dendo Grams, Hierarchical Trees
  • Dimensionality Reduction: Projections
    • Principal Component Analysis(PCA)
    • Kernel PCA
    • Supervised Dimensionality Reduction: LDANoSQL
  • Association Rule Mining
    • Apriori or Market Basket Analysis
NoSQL
  • Structured & Semistructured Data
  • MongoDB for Document Store DB
  • NoSQL Databases Role in Machine Learning: MongoDB
Deep Learning
  • Advanced Machine Learning
  • Neural Networks Intro
    • Artificial Neural Networks(ANN)
    • Deep Neural Networks
    • Convolutional Neural Networks(CNN)
    • Recurrent Neural Networks(RNN)
    • Stock Price Prediction using Neural Networks: Demo
    • Neural Net Concepts
    • Neurons as Nodes: Perceptrons
    • Dense & Sparse Neural Networks
  • Neuron Based approach: Benefits
    • Perceptrons
    • Learning Weights
    • Gradient Descent & Back Propagation
    • Activation Function & Feedforward Neural Networks
  • Installing Prerequisite Softwares
    • Tensorflow
    • Theano
    • Keras
  • 3 Layer Neural Network for Customer Churn Modeling
  • Online Learning(Reinforcement Learning)
  • Generative Adversarial Networks (GANs)
  • PyTorch
  • Image Processing Introduction
    • OpenCV for Image Processing in Python
    • Edge Detection
    • Eye & Nose Detection
    • Face Detection using Haar cascades
    • Optical Character Recognition using Neural Networks
    • Text Detection: Sliding Window
    • Character Segmentation
    • Character Classification
  • Synthetic Character Generation: Shearing & Scaling, Rotation
  • Revisiting Perceptrons
    • Coding a Text Classifier in Neural Networks
  • Advanced Neural Nets
  • Long Short Term Memory(LSTM) in RNN
  • Time Series Data(ARMA, ARIMA)
  • Unsupervised Learning using Hidden Markov Model(Tensorflow and Theano)
  • Tensorflow Deep Dive
  • Speech Recognition
  • Advanced Text Mining
  • Building & Deploying a Intelligent Chatbot
    • Data Preprocessing
    • Seq2Seq
    • Deploying the Chat Application
  • Computer Vision as AI
  • Image Recoginition and Classification
  • Deep Neural Networks Architecture revisited
  • Deep Convolutional Neural Network for Image Recognition
    • Convolutions
    • Pooling, Flattening
    • LeNet, Fully Connectected Feed Forward Network
    • Face Recognition using Convolutional Neural Network
    • Importing Pretrained Models
    • Running Convolutional Neural Networks on GPU for Image
  • Unsupervised Learning in Deep Neural Networks Revisited
    • urrent Advancements:
      • Self Organizing Maps(SOM)
      • Auto Encoders
      • Boltzman Machines
  • VGG, SDD, ResNet
  • Future Direction: Self Driving Cars, IIoT with AI, Drone based Parcel Delivery, etc
  • Conclusion

Course Outline

  • Advanced Python Programming Language is covered in Depth
  • Machine Learning & Data Visualization are covered in Python using language and also using Very advanced ML packages like Tensorflow, Theano and Keras
  • Data Visualization is covered with Python
  • All Machine Learning algorithms are covered in Depth, several algorithms are covered with real world solutions. Neural Networks and Deep Neural Nets are covered with real world examples
  • Knowledge about data, features & distribution, model building, accuracy are clearly covered
  • Basics to Advanced statistics are covered
  • Very advanced practical applications like Recommendation Engine, Threat Detection on Python

Benefits of our Courses

  • Exposure to advanced Data science concepts through experienced and senior Solution Architect
  • Presentations with Live Examples and real project scenarios, Business use cases
  • Optionally the students can work in our application(Real time project) based on their interest
  • Internships will be offered to high performing students
  • Profile Development & Placement assistance