Disable Preloader
  • Instructor
    Manaranjan Pradhan
  • Category
    ML and DL using python
  • Course Fees
    Quotation on request Rs.

Course name : Machine Learning Deep Learning using Python 5 Days

MACHINE LEARNING AND DEEP LEARNING USING PYTHON

Machine learning is one of the fastest-growing and most exciting fields out there, and deep learning represents its true bleeding edge. In this course, you’ll develop a clear understanding of the motivation for machine learning and deep learning models, and design intelligent systems that learn from complex and/or large-scale datasets.

We will introduce the basic concepts of statistics and machine learning models. We’ll also demonstrate how to train and optimize basic neural networks, convolutional neural networks, and long short term memory networks. Complete learning systems in TensorFlow will be introduced with working examples. You will also be introduced to H2O package to build a robust and scalable machine learning and deep learning model. You will learn to solve new classes of problems that were once thought prohibitively challenging, and come to better appreciate the complex nature of human intelligence as you solve these same problems effortlessly using deep learning methods.

WHO SHOULD ATTEND

Irrespective of type of industry (retail, e-commerce, manufacturing, real estate & construction, telecom, hospitality, banking, healthcare, IT, supply chain &logistic, etc.); data forms the crux of decision making. This course is designed for graduates and post graduates who will venture into the corporate set up and will be assisting the management in various decision making process. This course is equally suited to hone up analytical skills and business acumen of mid-level and senior level corporate professionals trying to understand the nuances of data science and help them the machine learning techniques an efficient way to generate insights for customers which in turn optimizes the bottom line of organizations.

HARDWARE AND SOFTWARE

  1. Participants should bring their laptop (preferably Windows 7 or higher/ Mac OS installed).
  2. Operating System (any of the following):
  • Mac OS X with XQuartz
  • Windows (Version XP or later) is required.
  1. Minimum 8 GB RAM on the system is advisable. 16GB RAM is preferable.

INSTALLATIONS:

More about anaconda can be found at https://docs.anaconda.com. Participants are expected to resolve any installation issues of the software prior to the commencement of the session.

PRE-REQUISITE & COURSE DELIVERABLE

  1. Participants should have basic programming skills. Participants are expected to spend time with the code set as a home assignment to leverage the classroom training hours to the fullest.
  2. High speed internet connection will be provided at the training venue.
  3. Deliverable: Python code and dataset. Soft copy of the content being covered  (PDF file)

COURSE OUTLINE

Day 1: Understanding Anaconda Framework platform and other useful packages in Python

Session 1–Introduction to Business Analytics

  • What is Business Analytics
  • Why is it needed and how industries are adopting it
  • Different components of analytics
  • Applications of analytics in different domains
  • Statistical learning vs. Machine learning
  • Artificial Intelligence, Machine Leaning and Deep Learning
  • What is Data Science and skills of a data scientist
  • Different types of machine learning algorithms–Supervised, Unsupervised and Reinforcement learning

Session 2 & 3–Introduction to Anaconda and Python

  • Overview of Anaconda framework
  • Python – Variables, objects, loops, conditions, function.
  • Python Data structures – lists, tuples, dictionaries, sets
  • Introduction to Numpy – ndarrays, ndarrays indexing, ndarrays datatypes and operations, statistical sorting and set operation
  • Introduction to Pandas – Data ingestion, descriptive statistics, visualization, frequent data operations, merging dataframes, parsing timestamps
  • Introduction to visualization – Matplotlib (Optional)
  • Introduction to H2O package, AutoML, Driverless AI (Optional)

Session 4 & 5–Basics of Statistics

  • Random Variable – Discrete and Continuous
  • Probability density function and Cumulative density function
  • Distribution Family – Gaussian Distribution, Standard Normal Distribution
  • Population and Sample
  • Central limit theorem
  • Demonstration of Central limit theorem on finance data
  • Hypothesis testing – Z test, t test, test for proportion,  analysis of variance (ANNOVA)
  • Covariance and Correlation

Day 2: Understanding regression and logistic regression and its implementation using Python

Session 1, 2 & 3–Lab 1: Linear Regression

  • Introduction to simple and multiple linear regression
  • Regression diagnostic–R-squared, t-test, F-test, error terms distribution, heteroscedasticity, identifying multi-collinearity and handling, AIC - model selection strategy
  • Common task framework for model evaluation – training and test set.
  • Case study using regression techniques and hands-on using Python code for regression

Session 4&5–Lab 2: Logistic Regression

  • Introduction to logistic regression
  • Logistic regression diagnostic: Wald statistics, Hosmer Lemeshow test, Classification Matrix, Sensitivity, Specificity, ROC Curve, precision, recall, F1-score
  • Strategy to find the optimal cut-off
  • Bias and variance in the model, Bias vs. variance tradeoff
  • Case study using logistic regression techniques and hands-on using Python code for regression

Day 3: Understanding supervised learning and gradient descent algorithm

Session 1 –Lab 2: Logistic Regression

  • Introduction to logistic regression
  • Logistic regression diagnostic: Classification Matrix, Sensitivity, Specificity, ROC Curve, precision, recall, F1-score
  • Strategy to find the optimal cut-off , cost of misclassification, F Score strategy
  • Bias and variance in the model, Bias vs. variance tradeoff
  • Case study using logistic regression techniques and hands-on using Python code for regression

Session 2–Lab 3: Decision Trees

  • Decision tree – Classification and regression trees (CART), Gini Index, Entropy
  • Decision tree – Chi-square automatic interaction detection (CHAID)
  • Case study using decision tree techniques
  • Hands-on using Python code

Session 3 & 4–Lab 4: Other Machine learning models (Ensemble Methods)

  • What is Machine learning
  • Different sampling strategies–Bootstrapping, Up–Sample, Down–Sample, Synthetic Sample, Cross–Validation Data
  • Introduction to Bagging–Random Forest, Other Bagging algorithms
  • Introduction to Boosting– Adaptive boosting, Other Boosting algorithms
  • Case study of an imbalanced data and application of sampling strategies & ensemble methods
  • Hands-on using Python code on an imbalanced data

Session 5 –Lab 5: Introduction to Gradient Descent

  • Hypothesis formulation for linear regression
  • Deriving the cost function for linear regression
  • Cost function– Intuition for linear regression with one parameter and two parameters
  • Gradient descent algorithm–application in linear regression
  • Hypothesis formulation for logistic regression
  • Deriving the cost function for logistic regression
  • Cost function– Intuition for logistic regression
  • Gradient descent algorithm–application in logistic regression
  • Hands-on using Python code to implement gradient descent for regression and logistic regression

Day 4: Understanding Deep Learning concepts and libraries

Session 1 – Introduction to Deep Learning

  • Understanding how machines learn
  • Understanding perceptron and multiplayer Neural Networks
  • Overview of Deep Learning Frameworks: Keras & Tensorflow

Session 2, 3 & 4 – Deep Dive into Deep Learning

  • Understanding Gradient Descent: Mini-batch and Stochastic
  • Overview Back Propagation, Cost Function & Optimizers
  • Writing a Deep Learning Algorithm from Scratch using Tensorflow
  • Developing a deep learning model using Keras
  • Developing a Regression & Classification Model using NN
  • NN Network Architecture & it’s hyper-parameters

Session 5 - Convolutions Neural Networks

  • Understanding Convolutions,  Filters, Max Pooling, Dropouts
  • Understanding Image Classification
  • Overview of different NN architectures – VGG Net, Lenet, googLenet
  • Building a CNN Model using Keras
  • Tensorboard for monitoring

Day 5: Understanding Deep Learning concepts and libraries

Session 1 - Convolutions Neural Networks

  • Understanding Convolutions,  Filters, Max Pooling, Dropouts
  • Understanding Image Classification
  • Overview of different NN architectures – VGG Net, Lenet, googLenet
  • Building a CNN Model using Keras
  • Tensorboard for monitoring

Session 2, 3 & 4: Sequence Models

  • Recurrent Neural Networks
  • Natural Language Processing and Word Embeddings
  • Sequence Models
  • Natural Language Processing - Building an RNN Model using Keras

Session 5: Model Evaluation

  • Creating Training, validation and Test Data Sets
  • Cross validations
  • Understanding Evaluation Metrics: RMSE, R-square, Confusion Matrix, Precision, Recall, Accuracy etc.

COURSE SCHEDULE

Day 1: Understanding Anaconda Framework platform and other useful packages in Python

This day will be about basic concepts in Python and statistics

Topic

Session

From

To

Introduction to business analytics

1

9 AM

10:15 AM

Introduction to Anaconda framework and Python

2

10:30 AM

11:45 AM

Introduction to Anaconda framework and Python…cont.

3

12:00 PM

1:15 PM

Introduction to statistics

4

2:15 PM

3:30 PM

Introduction to statistics…cont.

5

3:45 PM

5:00 PM

Day 2: Understanding regression and logistic regression and its implementation using Python

This day will be about underlying concepts of regression and logistic regression

Topic

Session

From

To

Lab 1: Linear Regression

1

9 AM

10:15 AM

Lab 1: Linear Regression…cont.

2

10:30 AM

11:45 AM

Lab 1: Linear Regression…cont.

3

12:00 PM

1:15 PM

Lab 2: Logistic Regression

4

2:15 PM

3:30 PM

Lab 2: Logistic Regression…cont.

5

3:45 PM

5:00 PM

Day 3: Understanding supervised learning and gradient descent algorithm

This day will be about underlying concepts of advanced machine learning algorithms

Topic

Session

From

To

Lab 2: Logistic Regression…cont.

1

9 AM

10:15 AM

Lab 3: Decision Trees

2

10:30 AM

11:45 AM

Lab 4: Ensemble Methods

3

12:00 PM

1:15 PM

Lab 4: Ensemble Methods…cont.

4

2:15 PM

3:30 PM

Lab 5: Introduction to Gradient Descent

5

3:45 PM

5:00 PM

Day 4: Understanding of Neural Networks, Deep Learning and Libraries

This day will be about underlying concepts of neural networks and CNN

Topic

Session

From

To

Introduction to Deep Learning

1

9 AM

10:15 AM

Deep dive into Deep Learning

2

10:30 AM

11:45 AM

Deep dive into Deep Learning…cont.

3

12:00 PM

1:15 PM

Deep dive into Deep Learning…cont.

4

2:15 PM

3:30 PM

Convolutions Neural Networks

5

3:45 PM

5:00 PM

Day 5: Advanced Concepts of Deep Learning and Applications

Application driven advanced concepts of RNN and model evaluation in Deep Learning

Topic

Session

From

To

Convolutions Neural Networks…cont.

1

9 AM

10:15 AM

Sequence Models

2

10:30 AM

11: 45 AM

Sequence Models…cont.

3

12:00 PM

1:15 PM

Sequence Models…cont.

4

2:15 PM

3:30 PM

Model Evaluation

5

3:45 PM

5:00 PM

 

Course Reviews

Average Rating:4.6

5 Stars24
4 Stars5
3 Stars2
2 Stars0
1 Star0

Comments

  • John Doe says:
    23/06/2014

    Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna et sed aliqua. Ut enim ea commodo consequat...

    Replay
  • John Doe says:
    23/06/2014

    Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna et sed aliqua. Ut enim ea commodo consequat...

    Replay
    John Doe says:
    23/06/2014

    Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna et sed aliqua. Ut enim ea commodo consequat...

    Replay
    John Doe says:
    23/06/2014

    Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna et sed aliqua. Ut enim ea commodo consequat...

    Replay
  • John Doe says:
    23/06/2014

    Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna et sed aliqua. Ut enim ea commodo consequat...

    Replay
Leave a Comment