Unsupervised learning in LSTM recurrent neural networks

被引：0

作者：

Klapper-Rybicka, M

Schraudolph, NN

Schmidhuber, J

机构：

[1] Stanislaw Staszic Univ Min & Met, Inst Comp Sci, PL-30059 Krakow, Poland

[2] Swiss Fed Inst Technol, Inst Computat Sci, CH-8092 Zurich, Switzerland

[3] IDSIA, CH-6928 Manno, Switzerland

来源：

ARTIFICIAL NEURAL NETWORKS-ICANN 2001, PROCEEDINGS | 2001年 / 2130卷

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

While much work has been done on unsupervised learning in feedforward neural network architectures, its potential with (theoretically more powerful) recurrent networks and time-varying inputs has rarely been explored. Here we train Long Short-Term Memory (LSTM) recurrent networks to maximize two in formation-theoretic objectives for unsupervised learning: Binary Information Gain Optimization (BINGO) and Nonparametric Entropy Optimization (NEO). LSTM learns to discriminate different types of temporal sequences and group them according to a variety of features.

引用

页码：684 / 691

页数：8

共 50 条

[1] Learning Statistical Scripts with LSTM Recurrent Neural Networks
Pichotta, Karl
Mooney, Raymond J.
THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2016, : 2800 - 2806
[2] An Unsupervised Learning Algorithm for Deep Recurrent Spiking Neural Networks
Du, Pangao
Lin, Xianghong
Pi, Xiaomei
Wang, Xiangwen
2020 11TH IEEE ANNUAL UBIQUITOUS COMPUTING, ELECTRONICS & MOBILE COMMUNICATION CONFERENCE (UEMCON), 2020, : 603 - 607
[3] Unsupervised Anomaly Detection With LSTM Neural Networks
Ergen, Tolga
Kozat, Suleyman Serdar
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2020, 31 (08) : 3127 - 3141
[4] An Unsupervised Neural Prediction Framework for Learning Speaker Embeddings using Recurrent Neural Networks
Jati, Arindam
Georgiou, Panayiotis
19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 1131 - 1135
[5] Scene Labeling with LSTM Recurrent Neural Networks
Byeon, Wonmin
Breuel, Thomas M.
Raue, Federico
Liwicki, Marcus
2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2015, : 3547 - 3555
[6] Economic LSTM Approach for Recurrent Neural Networks
Khalil, Kasem
Eldash, Omar
Kumar, Ashok
Bayoumi, Magdy
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2019, 66 (11) : 1885 - 1889
[7] auDeep: Unsupervised Learning of Representations from Audio with Deep Recurrent Neural Networks
Freitag, Michael
Amiriparian, Shahin
Pugachevskiy, Sergey
Cummins, Nicholas
Schuller, Bjoern
JOURNAL OF MACHINE LEARNING RESEARCH, 2018, 18
[8] Learning precise timing with LSTM recurrent networks
Gers, FA
Schraudolph, NN
Schmidhuber, J
JOURNAL OF MACHINE LEARNING RESEARCH, 2003, 3 (01) : 115 - 143
[9] Unsupervised Hebbian learning in neural networks
Freisleben, B
Hagen, C
COMPUTING ANTICIPATORY SYSTEMS: CASYS - FIRST INTERNATIONAL CONFERENCE, 1998, 437 : 606 - 625
[10] Gesture Classification Using LSTM Recurrent Neural Networks
Cifuentes, Jenny
Boulanger, Pierre
Pham, Minh Tu
Prieto, Flavio
Moreau, Richard
2019 41ST ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2019, : 6864 - 6867

← 1 2 3 4 5 →