CERTIFICATION COURSE
No. of Hours: 54 |
Certificate Validity: 2 Yr(s) |
Prerequisites
- Knowledge of Python, familiarity with control flow (if/else, for loops) and pythonic constructs (functions, classes, iterables, generators)
- Use of bash shell (or equivalent command prompt) and basic commands to copy and move files
- Basic knowledge of linear algebra (what is a vector, what is a matrix, how to calculate dot product)
Course Outcome
- To describe what Deep Learning is in a simple yet accurate way
- To explain how deep learning can be used to build predictive models
- To distinguish which practical applications can benefit from deep learning
- To install and use Python and Keras to build deep learning models
- To apply deep learning to solve supervised and unsupervised learning problems involving images, text, sound, time series and tabular data.
- To build, train and use fully connected, convolutional and recurrent neural networks
- To look at the internals of a deep learning model without intimidation and with the ability to tweak its parameters
- To estimate training costs for large models
- To re-use pre-trained models to shortcut training time and cost (transfer learning)
Target Audience
- Software engineers who are curious about data science and about the Deep Learning buzz and want to get a better understanding of it.
- Data scientists who are familiar with Machine Learning and want to develop a strong foundational knowledge of deep learning.
Module – 1
Data
– Tabular data
– Data exploration with Pandas code along
– Visual data Exploration
– Plotting with Matplotlib
– Unstructured Data
– Images and Sound in Jupyter
– Exercises
Machine Learning
– Machine Learning Problems
– Supervised Learning
– Linear Regression
Module – 2
Machine Learning
– Cost Function
– Cost Function code along
– Finding the best model
– Linear Regression code along
– Evaluating Performance
– Evaluating Performance code along
– Classification
– Classification code along
– Overfitting
– Cross Validation
– Cross Validation code along
– Confusion matrix
– Confusion Matrix code along
– Feature Preprocessing code along
Module – 3
Deep Learning Intro
– Deep Learning successes
– Neural Networks
– Deeper Networks
– Neural Networks code along
– Multiple Outputs
– Multiclass classification code along
– Activation Functions
Gradient Descent
– Derivatives and Gradient
– Back-propagation intuition
– Chain Rule
– Derivative Calculation
– Fully Connected Backpropagation
– Matrix Notation
– Numpy Arrays code along
– Learning Rate
– Learning Rate code along
– Gradient Descent
– Gradient Descent code along
– EWMA
– Optimizers
Module – 4
Convolutional Neural Networks
– Features from Pixels
– MNIST Classification
– MNIST Classification code along
– Beyond Pixels
– Images as Tensors
– Tensor Math code along
– Convolution in 1 D
– Convolution in 1 D code along
– Convolution in 2 D
– Image Filters code along
– Convolutional Layers
– Convolutional Layers code along
– Pooling Layers
– Pooling Layers code along
– Convolutional Neural Networks
– Convolutional Neural Networks code along
– Weights in CNNs
– Beyond Images
Module – 5
Recurrent Neural Networks
– Time Series
– Sequence problems
– Vanilla RNN
– LSTM and GRU
– Time Series Forecasting code along
– Time Series Forecasting with LSTM code along
– Rolling Windows
– Rolling Windows code along
Case Studies
Configuration:
1. Operating System: Ubuntu 18.04 LTS
2. RAM: 4 to 6 GB
3. Processor: i3 (Minimum) with Graphics Card
Timings:
6 Hrs per Week (Saturday and Sunday) : Weekend Batch and
6 Hrs per Week (Wed, Thu and Fri) : Weekdays Batch
2 Months
Weekly Assignment:
1. After every weekend session you’ll need to solve assignments until next week.
2. On completion of 1 module, you are required to appear exam.
3. All exams will be taken either on Center / Off site. When Off-site you will submit assignments via mail.
Final Exam:
A duration of 15 days, will be given after completion of Course
The Final exam will be a conducted once, in case of Failure; exam can be reappeared after another 1 month
Opportunities:
As first Opportunity after Passing exams, you will deployed on a Well monitored Live Project.
You are required to resolve the Problem statement with Expected outputs, with that you will be receiving a token of Completion Letter of respective Project.