in collaboration with
Branch - Applicable across all engineering branches
Deep Learning (also known as deep structure learning or hierarchical learning) is a part of the broader family of machine learning methods that is based on artificial neural networks. It is poised to have a market share of over $23 billion by 2024, thereby paving the way for a large number of jobs.
Application of Deep Learning and Neural Networks is a course that teaches the basic and advanced concepts of deep learning and neural networks supported by industry relevant business case studies. The course uses Python as the programming environment. Datasets required for the case studies can be obtained from the internet.
The course leverages the following to assist learners in building their practical and applied skills:
- Object identification and recognition using Convolutional Neural Networks (CNN)
- Face recognition using CNN (ResNet, VGG19)
- Sentence similarity using embeddings from Word2Vec, LASER
- Sentiment Analysis of tweets from social media using Long Short-Term Memory Networks (LSTM) and CNN
- Similar question detection using Siamese networks
A virtual hands-on environment is integrated within the course.
Students will have to leverage this environment to complete the industry assignment as well as to complete the Part B section of the summative assessment.+ Read More - Read Less
- Linear Algebra: Matrices and Vectors
- Calculus: Differentiation, Partial Derivatives and Gradient
- Statistics: Normal Distribution, Probability
- Basic Programming
- Data Processing using NumPy, Scipi, Matplotlib and Pandas
- Basic usage of Scikit, Scikit-learn packages in Python