Category: Entertainment

Presentation Description

Join our Machine learning training and placement and become Machine Learning Engineer Certified Professional.


Presentation Transcript

slide 1:

MACHINE LEARNING TRAINING COURSE CONTENT 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: 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 3: LINEAR REGRESSION  What is Linear Regression  Gradient Descent overview.  Gradient Descent Calculations.  R and Python Overview.  How to improve your model SECTION 4: 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.

slide 2:

 Maximum Likelihood Estimation.  Build an end to end model with Logistic Regression using scikit Learn.  How to build a model in the Industry SECTION 5: 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 6: K-NN  Distance based model with kNN.  Value of k – overview. SECTION 7: SUPPORT VECTOR MACHINESSVM  Power of SVM overview.  Why SVM  What is Kernel Functions  What are the Kernel Functions available  How to Build an OCROptical 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 8: DEEP NEURAL NETWORKS  Optimization methods overview.  Gradient Descent with Momentum RMSProp ADAM.  Learning Rate Decay.  Xavier Initialization.  Introduction to Keras and TensorflowTF  Deep Learning in Keras with TensorFlow as the backend. SECTION 9: UNSUPERVISED LEARNING

slide 3:

 Clustering overview.  k-means Clustering.  Hierarchical clustering. SECTION 10: PCA  Principal Component AnalysisPCA.  Maths behind PCA.  Engine Recommendation.  Content and Collaborative Filtering.  Market Basket Analysis  What is Apriori Rule SECTION 11: COMPUTER VISION  Image Detection Image Classification Localization.  Convolutional Neural NetworksCNN overview.  Strides Padding methods  Convolutional Padding and Fully Connected layers  Sliding Window  Edge Detection SECTION 12: ADVANCED COMPUTER VISION  YOLO ALgorithm – You Only Look Once  Introduction to classical networks like LeNet5  IoU  Introduction to Natural Language ProcessingNLP  Text Preprocessing  Lemmatization Stemming  Syntactical Parsing Entity Parsing  Develop a chatbot with the above concepts of NLP and Neural Networks Contact Info: Know more about Machine Learning New 30 Old 16A Third Main Road Rajalakshmi Nagar Velachery Chennai Opp. to MuruganKalyanaMandapam BOOK A FREE DEMO +91 9884412301 | +91 9884312236

authorStream Live Help