Applied AI with DeepLearning

The Introduction to deep learning module provides a comprehensive overview of linear algebra, deep feed forward neural networks, convolutional neural networks, recurrent neural networks, LSTMs, and various other essential concepts for building a strong foundation in deep learning.

The DeepLearning Frameworks module delves into popular frameworks like TensorFlow, Keras, PyTorch, and Apache SystemML, providing in-depth knowledge on installation, usage, features, and integration with other technologies. Additionally, this module covers neural network debugging, automatic differentiation, and model saving and loading techniques.

The DeepLearning Applications module focuses on practical applications such as anomaly detection, time series forecasting, image classification, and natural language processing. Students will learn to implement anomaly detectors, LSTM networks, and work with real-world datasets to gain hands-on experience in these areas.

The Scaling and Deployment module explores methods for parallel neural network training, scaling deep learning models on IBM Watson Machine Learning, and utilizing IBM Watson Visual Recognition and Natural Language Classifier for computer vision and text classification tasks. Additionally, it covers Apache SystemDS for deep learning neural network parallel training.