VISION AND COGNITIVE SERVICES

The course will cover the topics listed below:
- Introduction:
From human cognition to machine intelligence and cognitive systems; brief intro to artificial intelligence, cognitive computing and machine learning; the AI revolution: current trends and applications, major challenges.
- Cognitive Services:
Basic concepts; Language, Speech, and Vision services; major providers and APIs (IBM Watson, AWS, Google Cloud); enabling technologies.
- Machine Learning and applications:
Classification; intro to deep learning and representation learning; training and testing; evaluation measures; algorithm bias.
- Early Vision and Image Processing:
Machine perception; image formation, sampling, filtering and linear operators; image gradients, edges, corners; designing effective visual features (SIFT and gradient based features); image matching.
- Visual Recognition and beyond:
"Teaching computers to see": bag-of-features, spatial pyramids and pooling; representation learning in computer vision, convolutional neural networks; R-CNN and segmentation; image captioning, multi-modal scenarios and beyond the fully-supervised learning paradigm.
- Hands-on Practicals:
What's in the box? How to build a visual recognition pipeline; using cognitive services for image recognition/understanding; combining different services and modalities.