This is the last course (5th) in the Deep Learning Specialization, provided by Andrew Ng (DeppLearning.ai). After 37 videos (total about 6 hours) and 8 programming assignments (TensorFlow) I became familiar with sequence models and their exciting applications such as speech recognition, music synthesis, machine translation, natural language processing (NLP), and more.
The course introduced me to recurrent neural networks, a type that performs extremely well on temporal data, and several of its variants, including:
- LSTMs
- GRUs
- Bidirectional RNNs
It taught me how to improve the sequence models using an attention mechanism, an algorithm that helps the model decide where to focus its attention given a sequence of inputs. Then, I learned how to pair attention mechanisms to build the transformer architecture.
Credentials: