Mobile:+91 9600408821






New
Machine Learning Training in Chennai
curriculum
Syllabus
Machine Learning

Python based machine learning sessions cover classification, regression, clustering, natural language processing etc.,

  • Section 1: Introduction to ML
    • What is ML?
    • Why ML?
    • Opportunities in ML
    • What is ML models?
    • Why R and Python is popular?
  • Section 2: Python and ML Libraries Overview
    • Python
    • Pandas
    • Numpy
    • Scikit-learn
    • Matplotlib
    • Sns
  • Section 3: ML Model Overview
    • Introduction to ML Model.
    • Data Handling
    • Data Pre-processing
    • Types of ML Model.
    • Supervised and Unsupervised.
    • How to test your Data?
    • Cross validation techniques
  • Section 4: Linear Regression
    • What is Linear Regression?
    • Gradient Descent overview.
    • Gradient Descent Calculations.
    • R and Python Overview.
    • Gradient Descent Calculations.
    • How to improve your
  • Section 5: Overfitting
    • Overfitting Overview
    • How to use Linear Regression for Overfitting?
    • How to avoid Overfitting?
    • Bias-Variance Tradeoff.
    • Regularization – Ridge, LASSO
    • ANOVA, F tests overview.
    • What is Logistic Regression?
    • Classification with Logistic Regression.
    • Maximum Likelihood Estimation.
    • Build an end to end model with Logistic Regression using scikit Learn.
    • How to build a model in the Industry?
  • Section 6: Decision Trees
    • Why Decision Tree?
    • Entropy, Gini Impurity overview
    • Implement Overfitting.
    • How to improve the Decision Tree model without Overfitting?
    • Bagging, Boosting
    • Random Forest
    • AdaBoost, Gradient Boost
  • Section 7: K-NN
    • Distance based model with kNN.
    • Value of k – overview.
  • Section 8: SVM
    • Power of SVM overview.
    • Why SVM?
    • What is Kernel Functions?
    • What are the Kernel Functions available?
    • How to Build an OCR(Optical Character Reader) with the help of SVM and Kernel functions?
    • Neural Networks overview.
    • Why Neural Networks?
    • What is Neural Network Architecture?
    • How to build AND, OR, NOT, XOR, XNOR Logic Gates with Neural Network?
    • What is Forward & Backward Propagation?
    • List of Activation Functions.
    • Vanishing Gradient problem
  • Section 9: Deep Neural Networks
    • Optimization methods overview.
    • Gradient Descent with Momentum, RMSProp, ADAM.
    • Learning Rate Decay.
    • Xavier Initialization.
    • Introduction to Keras and Tensorflow(TF)
    • Deep Learning in Keras with TensorFlow as the backend.
  • Section 10: Unsupervised Learning
    • Clustering overview.
    • k-means Clustering.
    • Hierarchical clustering.
  • Section 11: PCA
    • Principal Component Analysis(PCA).
    • Maths behind PCA.
    • Engine Recommendation.
    • Content and Collaborative Filtering.
    • Market Basket Analysis
    • What is Apriori Rule?
  • Section 12: Computer Vision
    • Image Detection, Image Classification, Localization.
    • Convolutional Neural Networks(CNN) overview.
    • Strides, Padding methods
    • Convolutional, Padding and Fully Connected layers
    • Sliding Window
    • Edge Detection
  • Section 13: Advanced Computer Vision
    • YOLO ALgorithm – You Only Look Once
    • Introduction to classical networks like LeNet5
    • IoU
    • Introduction to Natural Language Processing(NLP)
    • Text Preprocessing
    • Lemmatization, Stemming
    • Syntactical Parsing, Entity Parsing
    • Develop a chatbot with the above concepts of NLP and Neural Networks
  • Section 14: Time Series Regression
    • RNN
    • GRU
    • LSTM
    • ARIMA & S-ARIMA
  • Section 15: Advanced ML
    • Online Learning
    • Advanced Keras
    • Advanced Tensorflow
    • Anomaly Detection
    • Boost Methods
Reviews

Lorem ipsum dolor sit amet, te eros consulatu pro, quem labores petentium no sea, atqui posidonium interpretaris pri eu. At soleat maiorum platonem vix, no mei case fierent. Primis quidam ancillae te mei.

4,5
Rated 5 out of 3 Ratings
5 stars
5 stars
5 stars
5 stars
5 stars
Sep 29, 2017 at 9:48 am

Nam egestas lorem ex, sit amet commodo tortor faucibus a. Suspendisse commodo, turpis a dapibus fermentum, turpis ipsum rhoncus massa, sed commodo nisi lectus id ipsum. Sed nec elit vehicula.

Sep 29, 2017 at 9:48 am

Nam egestas lorem ex, sit amet commodo tortor faucibus a. Suspendisse commodo, turpis a dapibus fermentum, turpis ipsum rhoncus massa, sed commodo nisi lectus id ipsum. Sed nec elit vehicula.

Sep 29, 2017 at 9:48 am

Nam egestas lorem ex, sit amet commodo tortor faucibus a. Suspendisse commodo, turpis a dapibus fermentum, turpis ipsum rhoncus massa, sed commodo nisi lectus id ipsum. Sed nec elit vehicula.

Members

Lorem ipsum dolor sit amet, te eros consulatu pro, quem labores petentium no sea, atqui posidonium interpretaris pri eu. At soleat maiorum platonem vix, no mei case fierent. Primis quidam ancillae te mei.