Abstract | ||
---|---|---|
Reservoir computing is a novel paradigm of neural network, offering advantages in low learning cost and ease of implementation as hardware. In this paper we propose a concept of reservoir computing consisting of a semiconductor laser subject to external feedback by a mirror, where input signal is supplied as modulation pattern of mirror reflectivity. In that system, non-linear interaction between optical field and electrons are enhanced in complex manner under substantial external feedback, leading to achieve highly nonlinear projection of input electric signal to output optical field intensity. It is exhibited that the system can most efficiently classify waveforms of sequential input data when operating around laser oscillation's effective threshold. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/978-3-319-46687-3_24 | Lecture Notes in Computer Science |
Keywords | Field | DocType |
Reservoir computing,Recurrent neural network,Sequential data processing,Laser,Silicon photonics,Energy efficiency | Nonlinear system,Computer science,Control theory,Electronic engineering,Modulation,Artificial intelligence,Silicon photonics,Pattern recognition,Waveform,Laser,Reservoir computing,Photonics,Optical field | Conference |
Volume | ISSN | Citations |
9947 | 0302-9743 | 1 |
PageRank | References | Authors |
0.35 | 6 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Seiji Takeda | 1 | 2 | 1.38 |
Daiju Nakano | 2 | 55 | 8.65 |
Toshiyuki Yamane | 3 | 61 | 9.08 |
Gouhei Tanaka | 4 | 51 | 11.80 |
Ryosho Nakane | 5 | 41 | 6.96 |
Akira Hirose | 6 | 426 | 67.35 |
Shigeru Nakagawa | 7 | 2 | 1.05 |