Professional Documents
Culture Documents
14 CS1AC16 Deep Learning
14 CS1AC16 Deep Learning
Neural networks:
Deep nets can discover hidden structures within unlabeled, unstructured data.
Training methodologies
Dropout – prevents overfitting – performing good on training data and poor on test data
At each training iteration some nodes are randomly dropped and the ones dropped previously are
added back with their original weights
Autoencoders – used for unsupervised learning
Aim is to reduce input data to get rid of redundant data – it trains a network to reduce inputs into a
meaningful encoded form
The way it works:
Create a network with multiple layers – the number of neurons must be less than number of inputs
except in the final layer where it must be equal to the number of inputs – the network is trained to
reproduce the original input:
Attach the network to a new set of layers and train to your labels:
Pooling neurons together reduces the amount of computation for later layers.