Our DEEP LEARNING program provides students with the fundamentals for building Neural Networks and Deep Learning training models. It covers Multi-Layer Feed Forward Networks, Restricted Boltzmann Machines, Autoencoders, Convolutional Neural Networks, Recurrent Neural Networks, Long Short Term Memory Networks, and Recursive Neural Networks with implementation using TensorFlow.
The program introduces the practical implementation of Deep Learning to solve real-world problems and familiarizes with essential Deep Learning architectural implementations in various applications such as Computer Vision, Recommender Systems, Text Analysis and Sequencing, and Natural Language Processing using TensorFlow.
The program will primarily use the Python programming language and assumes familiarity with linear algebra, probability theory, and programming in Python.
Deep Learning students will apply clustering techniques on real-world data, train Deep Neural Networks and Multi-Layer Perceptron with TensorFlow, build anomaly detection system by separating outliers, and use Deep Architectures for problem modeling.
The student will be able to construct data representations using deep neural nets, build models for sentiment analysis, train and build models for image classification, work with sequences using recurrent neural networks and use Deep Belief networks for classification.
The project work will build your technical skills by providing a methodological approach towards problem-solving using models in Deep Learning.