Neural Network

Recurrent Neural Network (RNN)

“Learning from the past”. Good for times series data.

https://karpathy.github.io/2015/05/21/rnn-effectiveness/ I thought RNNs don’t work from an interview, but they do? Well I wouldn’t really know since I haven’t realllyy tried with my A detailed look at the state of Flood Forecasting in climate science and the integration of Machine Learning Pipelines project.

https://www.youtube.com/watch?v=TQQlZhbC5ps&ab_channel=CodeEmporium

https://cs231n.github.io/rnn/

https://www.deeplearningbook.org/contents/rnn.html

Three types of models:

1. Vector-Sequence Models (ex: captioning an image)
2. Sequence-Vector Models (ex: Sentiment Analysis, converting a sentence into a number)
3. Sequence-sequence models (ex: Language translation)

Disadvantages:

1. Slow to train
2. Long sequences lead to vanishing / exploding gradients → Solution: Long Short-Term Memory