nnet – Ops related to neural networks¶
Aesara was originally developed for machine learning applications, particularly for the topic of deep learning. As such, our lab has developed many functions and ops which are particular to neural networks and deep learning.
conv– Ops for convolutional neural nets
basic– Basic Ops for neural networks
neighbours– Ops for working with images in convolutional nets
batchnorm– Batch Normalization
blocksparse– Block sparse dot operations (gemv and outer)
aesara.tensor.nnet.ctc– Connectionist Temporal Classification (CTC) loss