Training

Topic 1 : Classical Machine Learning

(15 lectures. Total 25 taught hours)

  • 8 in-class hands-on tutorials.
  • 8 real life assignments.
  • Lecture 1 Introduction to machine learning (Theory) (90 Minutes).
  • Lecture 2 Introduction to machine learning (Theory) (90 Minutes).
  • Lecture 3 Multivariate Linear Regression (Theory) (90 Minutes).
  • Lecture 4 Logistic Regression (Theory).
  • Lecture 5 Logistic Regression (Theory).
  • Lecture 6 Decision Tree Models (Theory Sessions).
  • Lecture 7 Ensemble Methods in Decision Tree Models (Theory and Python Hands-on) (90 Minutes).
  • Lecture 8 K-Means Clustering Theory and Python Hands-on (90 Minutes).
  • Lecture 9 PCA Theory and Python Hands-on.
  • Lecture 10 Feature Engineering and Feature Selection (Theory Session) (90 Minutes).
  • Lecture 11 Model Evaluation (Theory Session) (90 Minutes).
  • Lecture 12 Support Vector Machines (Theory Session) (90 Minutes).
  • Lecture 13 An Introduction to Deep Learning (90 Minutes).

Topic 2 : Python for Data Science

(10 to 15 100% hands-on lectures. Total 15 to 20 taught hours)

  • 100% in-class hands-on tutorials.
  • 5 real life assignments.
  • Lecture 1 Python Fundamentals Crash-Course (2 hours).
  • Lecture 2 Python for Data Analysis NumPy (2 hours).
  • Lecture 3 Pandas (2 hours).
  • Lecture 4 Data Visualization with Matplotlib (2 hours).
  • Lecture 5 Data Visualization with Seaborn (2 hours).
  • Lecture 6 Pandas Built-in Data Visualization Functions (2 hrs).
  • Lecture 7 Major Project 3 to 5 hours.

Topic 3 : Neural Networks / Deep Learning using Tensorflow

(10 to 12 100% hands-on lectures. Total 10 to 12 taught hours)

  • in-class theory and hands-on tutorials
  • 4 real life assignments.
  • Lecture 1 An Introduction to Deep Learning.
  • Lecture 2 ANN Simple Artificial Neural Networks.
  • Lecture 3 CNN Convolution Neural Networks.
  • Lecture 4 RNN Recurrent Neural Networks .
  • Lecture 5 Neural Nets Advanced Coding.
  • Lecture 6 Deep Learning Advanced Topics.
  • Lecture 7 DL Hyperparameter Tuning.
  • Lecture 8 Transfer Learning (Deep Neural Networks).
  • Lecture 9 DL Major Project.

Topic 4 : Natural Language processing (NLP) with Bert and Transformers

(8 to 10 100% hands-on lectures. Total 10 to 12 taught hours)

  • in-class theory and hands-on tutorials
  • 5 real life assignments.
  • Lecture 1 Common NLP terminology.
  • Lecture 2 Components o NLP.
  • Lecture 3 Steps in NLP analysis.
  • Lecture 4 Lexical Analysis.
  • Lecture 5 Syntactic Analysis.
  • Lecture 6 Tokenization in NLP.
  • Lecture 7 NLP stop words.
  • Lecture 8 Bag of words.
  • Lecture 9 Stemming.
  • Lecture 10 Lemmatization.
  • Lecture 11 Part of speech tagging.
  • Lecture 12 Lexical & Syntactic analysis .
  • Lecture 13 Semantic Analysis – Step by Step.
  • Lecture 14 Homographs, homophones, and homonyms.
  • Lecture 15 Polysemy.
  • Lecture 16 Ontology.
  • Lecture 17 Word sense disambiguation.
  • Lecture 18 Chinking in NLP.
  • Lecture 19 Relation Detection in NLP.
  • Lecture 20 Term-document matrix (co-occurrence matrix).
  • Lecture 16 Co-occurrence matrix.
  • Lecture 21 Semantic Analysis (Python Hands On).
  • Lecture 22 Distributional Semantics and Word Embeddings.
  • Lecture 23 Latent Semantic Analysis.
  • Lecture 24 Topic modelling.
  • Lecture 25 Tf-idf Matrix.
  • Lecture 26 LSA with tf-idf (Hand-on).
  • Lecture 27 CBOW - Continuous Bag of Words Model.
  • Lecture 28 Skip-gram model.
  • Lecture 29 WORD2VEC.
  • Lecture 30 GloVe - Global Vectors for Word Representation.
  • Lecture 31 STEP 4 in NLP. Disclosure integration.
  • Lecture 32 STEP 5 in NLP. Pragmatic Analysis.
  • Lecture 33 Rule-bases vs. Statistical NLP.
  • Lecture 34 A complete NLP Python Hands On.
  • Lecture 35 BERY.
  • Lecture 36 SPACY.
  • Lecture 37 NLTK.
  • Lecture 38 Transformer Models in General.
  • Lecture 39 Advanced Concepta in NLP.
  • Lecture 40 Major Project.