The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Training Recurrent Networks by Evolino
Abstract
In recent years, gradient-based LSTM recurrent neural networks (RNNs) solved many previously RNN-unlearnable tasks. Sometimes, however, gradient information is of little use for training RNNs, due to numerous local minima. For such cases, we present a novel method: EVOlution of systems with LINear Outputs (Evolino). Evolino evolves weights to the nonlinear, hidden nodes of RNNs while computing optimal linear mappings from hidden state to output, using methods such as pseudo-inverse-based linear regression. If we instead use quadratic programming to maximize the margin, we obtain the first evolutionary recurrent support vector machines. We show that Evolino-based LSTM can solve tasks that Echo State nets (Jaeger, 2004a) cannot and achieves higher accuracy in certain continuous function generation tasks than conventional gradient descent RNNs, including gradient-based LSTM.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Self-citationHarnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication
Jaeger, H., & Haas, H. (2004) · Science · doi:10.1126/science.1091277 · Cited by 3,811
Sims, K. (1994) · Proceedings of the 21st annual conference on Computer graphics and interactive techniques - SIGGRAPH '94 · doi:10.1145/192161.192167 · Cited by 1,005 · cited 1×
“more efficient and principled way is to search the space of RNN weight matrices [20,21,26,45,53,54] using evolutionary algorithms [1 3,31,41].”
MethodOptimization and applications of echo state networks with leaky- integrator neurons
Jaeger, H., Lukoševičius, M., Popovici, D., & Siewert, U. (2007) · Neural Networks · doi:10.1016/j.neunet.2007.04.016 · Cited by 948
Cited by
Deep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570
Self-citationGreff, K., Srivastava, R. K., Koutnik, J., Steunebrink, B. R., & Schmidhuber, J. (2017) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2016.2582924 · Cited by 6,955
“[28] proposed using a hybrid evolution-based method instead of BPTT for training but retained the vanilla LSTM architecture.”
MethodSelf-citationA Review of Recurrent Neural Networks: LSTM Cells and Network Architectures
Yu, Y., Si, X., Hu, C., & Zhang, J. (2019) · Neural Computation · doi:10.1162/neco_a_01199 · Cited by 5,591
Supervised Sequence Labelling with Recurrent Neural Networks
Graves, A. (2012) · Studies in Computational Intelligence · doi:10.1007/978-3-642-24797-2 · Cited by 3,120
Reservoir computing approaches to recurrent neural network training
Lukoševičius, M., & Jaeger, H. (2009) · Computer Science Review · doi:10.1016/j.cosrev.2009.03.005 · Cited by 2,956
Metadata
- Authors
- Schmidhuber, J., Wierstra, D., Gagliolo, M., & Gomez, F.
- Venue
- Neural Computation
- Publisher
- MIT Press - Journals
- Published
- 2007-03
- Volume
- 19
- Issue
- 3
- Pages
- 757-779
- ISSN
- 0899-7667 (ISSN-L)
- 1530-888X
- OpenAlex
- W2147107577
- Cited by
- 248
- References
- 4
- FWCI
- 15.76
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.