-
Notifications
You must be signed in to change notification settings - Fork 13
Session 2: Neural Networks for Classification
Chadwick Boulay edited this page Jan 18, 2019
·
1 revision
The second lesson introduces implements neural networks, building from the simplest 1-layer linear network in the previous lesson up to deep recurrent networks with non-linear activations. We will interact with real neurophysiological data throughout.
* Other activation functions
* Logistic
* RELU
* Calculating gradient
* Stacking layers
* BatchNorm
* Dropout
* ...
CNN
- Using single-channel ECoG and 1-D (temporal) convolutions.
- Using multi-channel ECoG with spatio-temporal convolutions.
- GRU
- LSTM