Deep Learning Lab
This course offers an opportunity to acquire practical experience in using TensorFlow to implement feedforward and recurrent neural networks (e.g., long short-term memory networks). Such networks currently achieve state-of-the-art results in many exciting tasks, such as object recognition, speech recognition, language translation, and learning to play games from experience. TensorFlow is an open source library developed by Google, and currently is the most popular choice among researchers and practitioners. Students will be evaluated through practical assignments.
- Nielsen, M. (2015). Neural networks and deep learning. Determination Press
- Bishop, C. M. (2006). Pattern Recognition and Machine Learning. Springer
- Murphy, K. P. (2012). Machine learning: a probabilistic perspective. MIT Press
- Graves, A. (2012). Supervised sequence labelling with recurrent neural networks. Springer