projects:localnn:start
Differences
This shows you the differences between two versions of the page.
Both sides previous revisionPrevious revisionNext revision | Previous revision | ||
projects:localnn:start [2015/02/11 16:07] – hj | projects:localnn:start [2015/05/11 20:12] (current) – hj | ||
---|---|---|---|
Line 10: | Line 10: | ||
network (LCNN), which imposes local connections within the neighboring neurons | network (LCNN), which imposes local connections within the neighboring neurons | ||
in the same layer in order to imitate the lateral inhibition. | in the same layer in order to imitate the lateral inhibition. | ||
+ | |||
+ | * Our maxout neuron based LCNN can achieve a 0.79% classfication error rate on the MNIST task without using pretraining and data augmentation. | ||
+ | * Our ReLU based LCNN can achieve a 15.0% word error rate in speech recognition on the Switchboard database. | ||
+ | |||
+ | To our knowledge, both results set the new state of the art performance on these tasks under similar training conditions. | ||
+ | |||
+ | **Reference: | ||
+ | [1] //Shiliang Zhang, Hui Jiang, Li-Rong Dai and Si Wei//, ``Locally Connected Deep Neural Networks,'' |
projects/localnn/start.1423670848.txt.gz · Last modified: 2015/02/11 16:07 by hj