A dual network for transfer learning with spike train data

K. Johnson; Wei Liu

doi:10.1007/978-3-319-26350-2_25

A dual network for transfer learning with spike train data

K. Johnson, Wei Liu

Research output: Chapter in Book/Conference paper › Conference paper › peer-review

Abstract

© Springer International Publishing Switzerland 2015. A massive amount of data is being produced in a continual stream, in real time, which renders traditional batch processing based data mining and neural network techniques as incapable. In this paper we focus on transfer learning from Spike Train Data, for which traditional techniques often require tasks to be distinctively identified during the training phase. We propose a novel dual network model that demonstrates transfer learning from spike train data without explicit task specification. An implementation of the proposed approach was tested experimentally to evaluate its ability to use previously learned knowledge to improve the learning of new tasks.

Original language	English
Title of host publication	AI 2015: Advances in Artificial Intelligence
Publisher	Springer
Pages	285-297
Volume	9457
ISBN (Print)	9783319263496
DOIs	https://doi.org/10.1007/978-3-319-26350-2_25
Publication status	Published - 2015
Event	A dual network for transfer learning with spike train data - Canberra, Australia Duration: 1 Jan 2015 → …

Conference

Conference	A dual network for transfer learning with spike train data
Period	1/01/15 → …

Access to Document

10.1007/978-3-319-26350-2_25

1 Doctoral Thesis

Continual learning of interval-based temporal patterns from event streams
Johnson, K., 2023, (Unpublished)
Research output: Thesis › Doctoral Thesis

File
140 Downloads (Pure)

Cite this

@inproceedings{9e89b316740545e5a8700555bfa16a03,

title = "A dual network for transfer learning with spike train data",

abstract = "{\textcopyright} Springer International Publishing Switzerland 2015. A massive amount of data is being produced in a continual stream, in real time, which renders traditional batch processing based data mining and neural network techniques as incapable. In this paper we focus on transfer learning from Spike Train Data, for which traditional techniques often require tasks to be distinctively identified during the training phase. We propose a novel dual network model that demonstrates transfer learning from spike train data without explicit task specification. An implementation of the proposed approach was tested experimentally to evaluate its ability to use previously learned knowledge to improve the learning of new tasks.",

author = "K. Johnson and Wei Liu",

year = "2015",

doi = "10.1007/978-3-319-26350-2_25",

language = "English",

isbn = "9783319263496",

volume = "9457",

pages = "285--297",

booktitle = "AI 2015: Advances in Artificial Intelligence",

publisher = "Springer",

address = "Netherlands",

note = "A dual network for transfer learning with spike train data ; Conference date: 01-01-2015",

}

TY - GEN

T1 - A dual network for transfer learning with spike train data

AU - Johnson, K.

AU - Liu, Wei

PY - 2015

Y1 - 2015

N2 - © Springer International Publishing Switzerland 2015. A massive amount of data is being produced in a continual stream, in real time, which renders traditional batch processing based data mining and neural network techniques as incapable. In this paper we focus on transfer learning from Spike Train Data, for which traditional techniques often require tasks to be distinctively identified during the training phase. We propose a novel dual network model that demonstrates transfer learning from spike train data without explicit task specification. An implementation of the proposed approach was tested experimentally to evaluate its ability to use previously learned knowledge to improve the learning of new tasks.

AB - © Springer International Publishing Switzerland 2015. A massive amount of data is being produced in a continual stream, in real time, which renders traditional batch processing based data mining and neural network techniques as incapable. In this paper we focus on transfer learning from Spike Train Data, for which traditional techniques often require tasks to be distinctively identified during the training phase. We propose a novel dual network model that demonstrates transfer learning from spike train data without explicit task specification. An implementation of the proposed approach was tested experimentally to evaluate its ability to use previously learned knowledge to improve the learning of new tasks.

U2 - 10.1007/978-3-319-26350-2_25

DO - 10.1007/978-3-319-26350-2_25

M3 - Conference paper

SN - 9783319263496

VL - 9457

SP - 285

EP - 297

BT - AI 2015: Advances in Artificial Intelligence

PB - Springer

T2 - A dual network for transfer learning with spike train data

Y2 - 1 January 2015

ER -

A dual network for transfer learning with spike train data

Abstract

Conference

Access to Document

Fingerprint

Research output

Continual learning of interval-based temporal patterns from event streams

Cite this