Deep learning enables faster and easier interpretation of large amounts of data and helps get meaningful information and actionable insights in almost all industries and domains. This course provides participants with theoretical underpinnings and practical training in deep learning with a focus on neural network techniques. Participants build, train, and apply Fully Connected Deep Neural Networks (FCNNS) for classification and regression needs and analyze necessary datasets for their deep learning applications based on neural network’s bias and variance analysis. Mechanisms to diagnose errors in these applications and prioritizing strategies to mitigate errors are also discussed in the course. To develop deep learning applications, students examine optimization algorithms, and build a Convolution Neural Networks and Recurrent Neural Networks including recent variations such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). Through lectures and hands-on sessions, participants grasp both theoretical principles and practical applications of applied deep learning and neural networks. TARGET AUDIENCE: All individuals including professionals, researchers, students, who are interested in Deep Learning. PREREQUISITES: Experience with Python programming.

Target Audience :
All individuals including professionals, researchers,students, who are interested in Deep Learning.