Abstract
We consider whether deep convolutional networks (CNNs) can represent decision
functions with similar accuracy as recurrent networks such as LSTMs. First,
we show that a deep CNN with an architecture inspired by the models recently
introduced in image recognition can yield better accuracy than previous convolutional and LSTM networks on the standard 309h Switchboard automatic speech recognition task. Then we show that even more accurate CNNs can be trained under the guidance of LSTMs using a variant of model compression, which we call model blending because the teacher and student models are similar in complexity but different in inductive bias. Blending further improves the accuracy of our CNN, yielding a computationally efficient model of accuracy higher than any of the other individual models. Examining the effect of “dark knowledge” in this model compression task, we find that less than 1% of the highest probability labels are needed for accurate model compression.
functions with similar accuracy as recurrent networks such as LSTMs. First,
we show that a deep CNN with an architecture inspired by the models recently
introduced in image recognition can yield better accuracy than previous convolutional and LSTM networks on the standard 309h Switchboard automatic speech recognition task. Then we show that even more accurate CNNs can be trained under the guidance of LSTMs using a variant of model compression, which we call model blending because the teacher and student models are similar in complexity but different in inductive bias. Blending further improves the accuracy of our CNN, yielding a computationally efficient model of accuracy higher than any of the other individual models. Examining the effect of “dark knowledge” in this model compression task, we find that less than 1% of the highest probability labels are needed for accurate model compression.
| Original language | English |
|---|---|
| Title of host publication | International Conference on Learning Representations (ICLR Workshop) |
| Number of pages | 13 |
| Publication status | Accepted/In press - 4 Feb 2016 |
| Event | 4th International Conference on Learning Representations - San Juan, Puerto Rico Duration: 2 May 2016 → 4 May 2016 https://iclr.cc/archive/www/doku.php%3Fid=iclr2016:main.html |
Conference
| Conference | 4th International Conference on Learning Representations |
|---|---|
| Abbreviated title | ICLR 2016 |
| Country/Territory | Puerto Rico |
| City | San Juan |
| Period | 2/05/16 → 4/05/16 |
| Internet address |