AI – Machine Learning

Machine Learning / Data Science / Artificial intelligence Course

In this training, you will learn about Machine Learning. What is machine learning? How can be developed machine learning project.

Prerequisite: Python, JavaScript Programming Knowledge

Duration: 20 Hours

Actual Price: ₹6000/-
Offer Price: ₹4800/-
20% discount. Limited Offer! Only for you.

Class Type: Online/Offline

Course Details:

  • What is Machine Learning? and How It works?
  • Introduction to neural networks
  • Training The model
  • Types of Machine Learning
  • The Linear Model
  • Linear Model and Multiple Inputs
  • Multiple Inputs and Outputs
  • Graphical Representation
  • The Object Function
  • L2-norm loss
  • Cross Entropy loss
  • One Parameter gradient descent
  • N-Parameter gradient descent
  • Using Python with Jupyter Notebook
  • Installing Anaconda
  • Installing TensorFlow
  • Introduction of TensorFlow
  • Types of file formats in TensorFlow
  • Inputs, outputs, targets, weights, biases – model layout
  • Loss function and gradient descent – introducing optimizers
  • Model output
  • Going deeper: Introduction to deep neural networks
  • Layers
  • What is a deep net?
  • Understanding deep nets in depth
  • Why do we need non-linearities
  • Activation functions
  • Softmax activation
  • Backpropagation
  • Backpropagation – visual representation
  • Backpropagation. A peek into the Mathematics of Optimization
  • Overfitting
  • Underfitting and overfitting
  • Underfitting and overfitting – classification
  • Training and validation, Test
  • N-fold cross-validation
  • Early stopping
  • Initialization – Introduction
  • Types of simple initializations
  • Xavier initialization
  • Gradient descent and learning rates<
  • Stochastic gradient descent
  • Gradient descent pitfalls
  • Momentum
  • Learning rate schedules
  • Learning rate schedules. A picture
  • Adaptive learning rate schedules
  • Adaptive moment estimation
  • Preprocessing introduction
  • preprocessing
  • Standardization
  • Dealing with categorical data
  • One-hot and binary encoding

Practical Project Implementation