Interactive session, Monday April 17
- First hour: Guest lecture from Elliptic Labs where they will explain and demonstrate "Classification of Sensor data using Neural Networks"
- Second hour: Review of Deep learning plus newer developments including ChatGPT
Weekly lecture:
- There were some mistakes with the indices on the slides no 24 and 27 in the second video. They are correct in the pdf slides.
- May 12: I spotted another typo in slides no 24 and 27. At one place it was written w_{m} instead of w_{j, m}. This is now corrected and the link is to the corrected version.
- Because we have rescheduled this semester, the internal numbering of the slides and videos show week 10.
Slides
Video Recordings:
- The deep learning revolution
- Deep feed-forward neural networks
- Convolutional neural networks and image processing
- Recurrent neural networks and language processing
Recommended readings:
There are no mandatory readings this week.
For the Deep-learning revolution, there are several popular introductions. The Great AI Awakening, from NY Times, Dec 2016, is an interesting report from the time when the media started to recognize the revolution. For they who want to dig deeper into the revolution, we recommend the recent book by Melanie Mitchell, Artificial Intelligence, 2019.
If you are interested in knowing more about CNNs, this page from the Stanford course CS231n, is highly recommended. We have had problems finding presentations of RNNs which go beyond the slides without being highly technical.
If you are ready for practical experience with deep learning, you may start with Paolo Perrotta, Programming Machine Learning (in O'Reilly library), Ch. 16 ff. which uses Tensorflow and Keras. If you are ready for go one step further, you may proceed with Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow, (2. ed.) by Aurelien Geron.