%0 Journal Article %1 gonnet2019indylstms %A Gonnet, Pedro %A Deselaers, Thomas %D 2019 %K deep-learning memory %T IndyLSTMs: Independently Recurrent LSTMs %U http://arxiv.org/abs/1903.08023 %X We introduce Independently Recurrent Long Short-term Memory cells: IndyLSTMs. These differ from regular LSTM cells in that the recurrent weights are not modeled as a full matrix, but as a diagonal matrix, i.e.\ the output and state of each LSTM cell depends on the inputs and its own output/state, as opposed to the input and the outputs/states of all the cells in the layer. The number of parameters per IndyLSTM layer, and thus the number of FLOPS per evaluation, is linear in the number of nodes in the layer, as opposed to quadratic for regular LSTM layers, resulting in potentially both smaller and faster models. We evaluate their performance experimentally by training several models on the popular and CASIA online handwriting datasets, as well as on several of our in-house datasets. We show that IndyLSTMs, despite their smaller size, consistently outperform regular LSTMs both in terms of accuracy per parameter, and in best accuracy overall. We attribute this improved performance to the IndyLSTMs being less prone to overfitting.

@article{gonnet2019indylstms, abstract = {We introduce Independently Recurrent Long Short-term Memory cells: IndyLSTMs. These differ from regular LSTM cells in that the recurrent weights are not modeled as a full matrix, but as a diagonal matrix, i.e.\ the output and state of each LSTM cell depends on the inputs and its own output/state, as opposed to the input and the outputs/states of all the cells in the layer. The number of parameters per IndyLSTM layer, and thus the number of FLOPS per evaluation, is linear in the number of nodes in the layer, as opposed to quadratic for regular LSTM layers, resulting in potentially both smaller and faster models. We evaluate their performance experimentally by training several models on the popular \iamondb and CASIA online handwriting datasets, as well as on several of our in-house datasets. We show that IndyLSTMs, despite their smaller size, consistently outperform regular LSTMs both in terms of accuracy per parameter, and in best accuracy overall. We attribute this improved performance to the IndyLSTMs being less prone to overfitting.}, added-at = {2019-03-21T00:49:48.000+0100}, author = {Gonnet, Pedro and Deselaers, Thomas}, biburl = {https://www.bibsonomy.org/bibtex/24f29b2003670001bbdafa7689e986f0a/kirk86}, description = {IndyLSTMs: Independently Recurrent LSTMs}, interhash = {cf29590b3ad0a76f6c7d735dc7309c3b}, intrahash = {4f29b2003670001bbdafa7689e986f0a}, keywords = {deep-learning memory}, note = {cite arxiv:1903.08023Comment: 8 pages, submitted to ICDAR 2019}, timestamp = {2019-03-21T00:49:48.000+0100}, title = {IndyLSTMs: Independently Recurrent LSTMs}, url = {http://arxiv.org/abs/1903.08023}, year = 2019 }