Machine Language & Deep Learning
Duration: 6 Months

119,999.00

Category:

 

📜 Course Description

The primary goal of this course is to demystify Machine Learning  &

Deep Learning and get the students acquainted with end-to-end Mastery of the complete process, involving understanding problem, Understanding data,  Feature Selection, Algorithms, Evaluation, Optimization and Deployment of models. This course is specifically designed as per the requirements and opportunities in the job market. The course covers complete Python and all the essential Python tools and Libraries for Data Analysis, Wrangling, Cleansing and Visualization . It’s more focused on teaching the mainstream and in-demand tools with stable versions. Covers all the prerequisites & the foundation technologies.

🎯 Course Goals

Master skills with in-depth learning & get acquainted with end-toend Machine Learning & Deep Learning expertise right from foundation to building solutions for real problems.

Targeted Job Roles

  • Machine Learning Engineer
  • Deep Learning Engineer
  • AI Specialist
  • NLP Engineer
  • AI / ML Engineer
  • Data Analyst / Data Scientist (Machine Learning)

🛠️Tools Covered

Python, Anaconda, Jupyter Notebook Numpy, Panadas,

Matplotlib, Seaborn, Scikit-learn, Tensorflow, Keras, PyTorch,

Google Colab, AWS Sagemaker, Apache Spark

📝Requirements

  • Your own Laptop, If you don’t have sufficient resources

(Memory, CPU, Disk) to practice, you can still complete all the

 

activities in the Cloud.

  • Internet Connection
  • Cloud Account: AWS (Free tier)

📝Curriculum

INTRODUCTION TO ML

  • Understanding Machine Learning
  • Understanding Data Science
  • Understanding AI
  • Timeline of Machine Learning
  • Use Cases

JUST ENOUGH PYTHON

  • Introduction to Python
  • Python variables, integers, indentation
  • Python Datatypes / Data structures
  • Statements
  • Operator / Loops / Functions
  • Exception Handling

PYTHON ML ECOSYSTEM

  • Introduction to Numpy, SciPy, Pandas, Matplotlib, Seaborn
  • Introduction to Scikit-learn, Tensorflow, Keras

DATA ANALYSIS (PYTHON)

  • Understanding Machine Learning
  • Understanding Data Science
  • Understanding AI
  • Timeline of Machine Learning
  • Use Cases

DATA WRANGLING (PYTHON)

  • Introduction to Python
  • Python variables, integers, indentation
  • Python Datatypes / Data structures
  • Statements
  • Operator / Loops / Functions
  • Exception Handling

DATA VISUALIZATION (PYTHON)

  • Introduction to Python
  • Python variables, integers, indentation
  • Python Datatypes / Data structures
  • Statements

LINEAR ALGEBRA  FOR ML

  • Why Math?
  • Mathematical Objects (Scalar, Vector, Matrix, Tensor)
  • Linear Algebra Notation
  • Linear Algebra Arithmetic / Stats
  • Matrix Operations / Factorization

STATISTICS FOR ML

  • Statistical core concept
  • Descriptive Statistics
  • Inferential Statistics
  • Hypothesis Testing

PROBABILITY FOR ML

  • Probability & Conditional Probability
  • Joint, Marginal, and Conditional Probability
  • Bayesian probability theory
  • Probability Distributions
  • Information
  • Probability Algorithms

DEMYSTIFYING ML

  • 360-degree view
  • ML the complete Process
  • Algorithms with Use Cases
  • Common terms and Concepts
  • ML vs DL
  • ML in production

ESSENTIAL CONCEPTS IN ML

  • ML Glossary
  • Building Model / Complete Process
  • ML Common Concepts
  • Common Properties and Assumption

TYPES OF ML ALGORITHMS

  • Classification Algorithms
  • Regression Algorithms
  • Regularization Algorithms
  • Decision Tree Algorithms
  • Instance-based Algorithms
  • Clustering Algorithms
  • Dimensionality Reduction Algorithms
  • Bayesian Algorithms
  • Association Rule Learning Algorithms
  • Ensemble Algorithms

INTRODUCTION TO ML LIB

  • Introduction to Scikit-learn
  • Scikit-learn Dependencies
  • Hands-on

DATA PREPROCESSING

  • Need
  • Handling missing values
  • Handling features
  • Mean removal
  • Variance scaling

REGRESSION

  • Single / Multivariate Linear Regression
  • OLSR
  • Polynomial Regression
  • Lasso / Rigid Regression

CLASSIFICATION

  • Logistic Regression
  • Support Vector Machine
  • K-Nearest Neighbor
  • Decision Tree / Random Forest
  • Naïve Bayes Classifiers
  • Linear Discriminant Analysis

CLUSTERING

  • k-Means
  • Mini-Batch K-Means
  • Mean-Shift Clustering
  • Affinity Propagation
  • DBSCAN
  • Mixture of Gaussians

DIMENSION REDUCTION

  • Principal Component Analysis
  • Linear Discriminant Analysis

RECOMMENDATION SYSTEM

  • Understanding Recommendation Systems
  • Content-Based Recommender system
  • Collaborative Filtering

NATURAL LANGUAGE PROCESSING

  • Lexical Processing
  • Syntactical Processing
  • Semantic Processing
  • Introduction to NLTK
  • Text Classification
  • Sentiment Analysis
  • Topic Modelling

ML ON BIG DATA (SPARK)

  • Introduction to Apache Spark
  • Apache Spark Essentials
  • RDD
  • Running ML Techniques and algorithms using Apache Spark

DEMYSTIFYING DEEP LEARNING

  • 360-degree view
  • Why Deep Learning
  • Timeline of AI and Deep learning
  • Understanding Neural Networks
  • Biological vs Artificial Neuron
  • Use Cases

ESSENTIAL CONCEPTS IN DL

  • Neurons
  • Neural Network
  • Deep Neural Network / DL
  • Activation Functions
  • Layers / Weights
  • Forward / Back Propagation

DEEP LEARNING LIBS

  • History of DL Libraries
  • Introduction to Theano
  • Introduction to Tensorflow
  • Introduction to Keras
  • Introduction to Mxnet

NEURAL NETWORK

  • Neurons
  • Biological Neuron vs Artificial Neuron
  • Neurons to Neural Network
  • Training a Neural Network
  • Different types of Neural Networks
  • Gradient Descent
  • Activation and Loss functions
  • Hyperparameter tuning
  • Tensor Flow & Keras

RECURRENT NN (RNN)

  • Why RNN?
  • RNN vs ANN
  • Advantages of RNN
  • Use Cases
  • Challenges of RNN
  • RNN with TensorFlow (Projects)

CONVOLUTIONAL NN (CNN)

  • Why CNN?
  • Advantages of CNN
  • Computer Vision
  • Use Cases
  • Challenges of CNN
  • RNN with TensorFlow (Projects)

ARTIFICIAL NN (ANN)

  • Why ANN?
  • Feed Forward Neural Network
  • Advantages of ANN
  • Use Cases
  • Challenges of ANN ANN with TensorFlow (Projects)

NOTE:

  • Each module includes the Hands-On Real-world Project related to the Subject.