About the Program
This course is designed to provide exposure to the fundamentals of Artificial Intelligence and Deep Learning. Participants will learn to apply deep learning techniques to solve real-world research and industry problems. Hands-on training and practice sessions will help participants gain confidence on deep learning concepts by creating their own neural networks, object detection models, etc. The course will be useful for faculty of engineering and sciences who are interested in learning recent AI trends and their applications in areas like image processing, computer vision, and robotics.
Technologies and Tools Covered
- Python IDE
- Anaconda Navigator
- Jupyter Notebook
Importance of the Course
- Artificial intelligence and Deep learning have long since found their way into large parts of industry. Success has most recently been achieved in autonomous driving, medical image processing or material testing. In future, Artificial Intelligence (AI) will play an even greater role in numerous industries and scenarios. To remain fit for this future, companies have to deal with the basics of AI and machine learning.
- These basics are imparted in the Internship, which bundles the sheer flood of information and offers you a compact overview of theory and practice in Deep learning. You receive the hands-on knowledge you need to integrate the enormous potential of artificial intelligence into your product portfolio and value chain.
- This workshop is very practice-oriented. Half of it consists of applied exercises on a consistent topic. You will learn the relevant methods and practices around Deep learning while focusing on artificial neural networks, the basis for Machine learning.
1.Introduction to Python and Machine Learning
|1||Introduction to Python Programming|
|2||Software Installation IDE, Anaconda Navigator|
|3||Introduction to Machine Learning and Deep Learning Package|
|4||Training Machine Learning Model|
|5||Inference from Machine Learning Model|
2. Keras Fundamentals for Deep Learning
Here’s how to make a Sequential Model and a few commonly used layers in deep learning.
Example of how to make convolutional layer as the input layer with the input with filters of size and use ReLU as an activation function. How to down sample the input representation, use MaxPool2d and specify the kernel size. Adding a Fully Connected Layer with just specifying the output Size. Adding dropout layer with Compiling, Training, and Evaluate
|1||Installing Procedure of KERAS|
|2||Loading a Data|
|3||Define a Neural network in keras|
|4||Compile a Keras model using the efficient numerical backend.|
|5||Train a model on data.|
|6||Evaluate a model on data and make predictions with the model.|
3. CNN and Project Working
|1||Building a CNN model|
|2||CNN for image classification|
|3||Introduction to LSTM, GRU|
|4||Applications in machine translation language modelling and sentiment classification.|
Projects & Assignments
Practical 1 : Using CSV Dataset.
Practical 2 : Using Image Classification.
Practical 3 : Building an AI application for sentiment classification
Practical 4 : AI Face Recognition
The Program is a mix of Theory sessions, Quizzes, Hands-on Sessions, Interaction with Experts, Assignments, and Practical Exercises. Maximum Impetus is given to Hands-on Sessions so as to enable the participants with the maximum knowledge transfer and satisfaction. The ratio of the theory, practical sessions will be 30:70.
Python Functions & Syntaxes
ML Concepts & Processing
Anaconda - Numpy
ML & Data Visuvalisation
K Means - Clustering
Ai using Python Lesson 9
Deep Neural Networks
Stemming | Lemmatization
Technical content and lecture sessions along with the course curriculum are good. Thank you
Mam was so goods at teaching mam cleared all the doubts and made the topics easy to understand