This course provides the knowledge to construct and use deep neural networks for image and text analysis. The course starts from the basic concepts to understand, train and test neural networks for classification and regression. It introduces image analysis and then evolves to (Fully) Convolutional Neural Networks for image classification, object detection, and (semantic/instance) segmentation. In the sequence, it provides an introduction to text analysis and then covers Recurrent Neural Networks, Attention, Transformers and applications in text analysis.
Prior knowledge in optimization, linear algebra, statistics, machine learning, image/text processing and analysis is important, but the basic concepts are provided whenever they are required.
It is important the student can code in Python and desirable prior knowledge in PyTorch, and other packages usually used in python scripts for image and text processing, graphics display, and machine learning.