### Machine Learning & Python  Trainig and Internship

### Machine Learning & Python ##### What you'll learn
• Machine Learning with Deep Learning
• Python ##### Highlights
• Certifications – Certificate will be provide after complication of the course.
• Available –Online / Offline Learning (No recorded lecture / live session of each class).
• 60 hrs Course..
• Rich course content for master learning
• Pay after six demo class.
• 70% Hands on Course + 30 %Theory.
• One MCQ and one case study is compulsory for completion of course..
• Certificate will generated after successfully completion of the course. ##### Course Fee
• Corporate Trainer :25000 INR (18% GST Extra)
• Students:12000 INR (18% GST Extra) ##### Prerequisites
• Mathematics and Statistics.
• Python ### Introduction to Python

Level-1

• Why to use python ?
• Python IDE
• Simple Program in Python
• Numbers And Math functions
• Common Errors in Python ### Introduction to Python

Level-2

• Variables & Names
• String basics
• Conditional statements
• Assignment 2
• Functions
• For and While ### Introduction to Python

Level-3

• Functions as arguments
• List,Tuple and Dictionaries
• List Comprehension
• File handling
• Class and Objects ### Introduction to Python

Level-4

• Numpy
• Pandas
• List Comprehension
• Matplotlib
• Seaborn
• Ggplote
• Tensorflow ### Module-2

• Introduction to Machine Learning. Different types of learning like supervised learning, unsupervised learning, and semi supervised learning, Reinforcement learning etc.
• Linear Algebra: Scalars, Vectors, Tensors, Basic Operations, Norms, Linear Combinations Span Linear Independence, Matrix Operations Special Matrices Matrix Decompositions.
• Machine Representation of Numbers, Overflow, Underflow, Condition Number, Derivatives, Gradient, Hessian, Jacobian, Taylor Series.
• Statistical tools: Mean, Mode, Median, Standard deviation, Variance, Covariance and correlation. F-Score, Goodness of Fit. Confusion Matrices.
• Probability Theory: Random Variable, Binomial Distribution, Poisson Distribution, Hypergeometric Distribution, Methods of Assigning Probabilities, Structure of Probability, Marginal, Union, Joint, and Conditional Probabilities, Addition Laws, Multiplication Law, Conditional Probability, Bayes’ Rule.
• Optimization : Unconstrained Optimization, Introduction to Constrained Optimization, Introduction to Numerical Optimization, Gradient Descent Proof of Steepest Descent Numerical Gradient Calculation Stopping Criteria. ### Module-3

Machine Learning Tools-1

A Linear Regression Example, Linear Regression Least Squares Gradient Descent, Generalized Function for Linear Regression, Bias-Variance Trade Off, Gradient Descent Algorithms, Stochastic gradient descent, Batch Gradient descent. Learning rate, Multi-dimensional linear regression, Minimum square error, least square error, Absolute error. ### Module-4

Classification Techniques

Logistic Regression, Binary Entropy cost function, OR Gate Via Classification, NOR, AND, NAND Gates, XOR Gate, Differentiating the sigmoid, Gradient of logistic, regression, Multinomial Classification- Introduction, Multinomial Classification - One Hot Vector, Multinomial Classification – Softmax, Schematic of multinomial logistic regression, Various decision boundaries and their differentiation ### Module-5

Artificial Neural Networks

Multilayer Perceptron Neuron: Introduction, Model, Learning, Evaluation, Geometry Basics, Geometric Interpretation, Perceptron: Learning - General Recipe, Learning Algorithm, Perceptron: Learning - Why it Works?, Perceptron: Learning - Will it Always Work?, Perceptron: Evaluation, A simple deep neural network, A generic deep neural network, Understanding the computations in a deep neural network, The output layer of a deep neural network, Output layer of a multi-class classification problem, How do you choose the right network configuration, Loss function for binary classification, Learning Algorithm (non-mathy version),

Backpropagation

• Setting the context-
• Chain rule of derivatives
• Applying chain rule across multiple paths
• Applying Chain rule in a neural network
• Computing Partial Derivatives w.r.t. a weight
• Computing Derivatives w.r.t. Hidden Layers
• Computing Partial Derivatives w.r.t. a weight
• Computing Partial Derivatives w.r.t. a weight when there are multiple paths. ### Module-6

Operation on Different Machine Learning Tools

Support Vector machine, Radial Basis function, K-Nearest neighbours, Self-Organising Map, Naïve Bayes, MLE Intro, and Principal Component Analysis, Singular Value Decomposition. ### Module-7

Convolution Neural Networks

The convolution operation, Relation between input size, output size and filter size, Convolutional Neural Networks, CNNs (success stories on ImageNet), Image Classification continued (GoogLeNet and ResNet), Visualizing patches which maximally activate a neuron, Visualizing filters of a CNN, Occlusion experiments, Finding influence of input pixels using backpropagation, Guided Backpropagation, Optimization over images, Create images from embedding, Deep Dream, Deep Art, Fooling Deep Convolutional Neural Networks ### Module-8

Machine Learning

• Introduction to Machine learning,
• various type of learning like supervised learning, unsupervised learning, semi supervised learning, Reinforcement learning etc
• Bias and Variance, Learning parameters