What is Deep Learning?know about deep learning!
Deep Learning
What is Deep Learning
As we said above the deep learning is the branch of Machine Learning.
the Deep learning is depends on Human brains Neutral networks.
the deep learning is stared in NLP(national language process).
Deep Learning capable to Focus on right features by themselves,
requiring little guidance of the Programmer.
the models also partially solve dimensionality Problems.
The Idea behind the Deep learning is to build Learning Algorithms that Act as BRAIN.
A collection of statistical Machine Learning techniques used to learn feature hierachies often based on artificial intellegance.
Application of DeepLearning
Large-scale automatic speech recognition is the first and most convincing successful case of deep learning. LSTM RNNs can learn "Very Deep Learning" tasks that involve multi-second intervals containing speech events separated by thousands of discrete time steps, where one time step corresponds to about 10 ms. LSTM with forget gates is competitive with traditional speech recognizers on certain tasks.
The initial success in speech recognition was based on small-scale recognition tasks based on TIMIT. The data set contains 630 speakers from eight major dialects of American English, where each speaker reads 10 sentences. Its small size lets many configurations be tried. More importantly, the TIMIT task concerns phone-sequence recognition, which, unlike word-sequence recognition, allows weak phone bigram language models. This lets the strength of the acoustic modeling aspects of speech recognition be more easily analyzed. The error rates listed below, including these early results and measured as percent phone error rates (PER), have been summarized since 1991.
| Method | PER (%) |
|---|---|
| Randomly Initialized RNN | 26.1 |
| Bayesian Triphone GMM-HMM | 25.6 |
| Hidden Trajectory (Generative) Model | 24.8 |
| Monophone Randomly Initialized DNN | 23.4 |
| Monophone DBN-DNN | 22.4 |
| Triphone GMM-HMM with BMMI Training | 21.7 |
| Monophone DBN-DNN on fbank | 20.7 |
| Convolutional DNN | 20.0 |
| Convolutional DNN w. Heterogeneous Pooling | 18.7 |
| Ensemble DNN/CNN/RNN | 18.3 |
| Bidirectional LSTM | 17.9 |
| Hierarchical Convolutional Deep Maxout Network | 16.5 |
Comments
Post a Comment