Ghent University On Implementing Reservoir Computing Benjamin Schrauwen
Ghent University On Implementing Reservoir Computing Benjamin Schrauwen Electronics and Information Systems Department Ghent University – Belgium December 9 2006 - NIPS 2006
Outline • Introduction • Software: Reservoir Computing Toolbox • Hardware: Digital spiking neurons • Future hardware • Conclusions On Implementing Reservoir Computing NIPS 2006 – December 9 2/31
Introduction • LSM, ESN, BPDC, SDN, … are all the same concept, just use different nodes and topologies: Reservoir Computing • How to evaluate RC performance across node types? • Opensource MATLAB toolbox for reservoir computing research • A box of tools + examples + a large scale explorer • Because all techniques in single flow: able to focus on specific influence of: • Topology • Node type • Reservoir adaptation On Implementing Reservoir Computing NIPS 2006 – December 9 3/31
Reservoir Computing Toolbox • Generic way to construct topologies and weight scaling • Various node types supported: linear, TLG, tanh, fermi, spiking (LIF, synapse models, dynamic synapses) • Event based simulator for spiking neurons: ESSpi. NN • Supports batching for large datasets • Currently focused on off-line training (on-line in construction) • Resampling and post-processing pipeline • Linear, ridge-regression, non-linear readout • Cross-validation, grid-search • Reservoir adaptation On Implementing Reservoir Computing NIPS 2006 – December 9 4/31
The RC Toolbox Input data generation Topology Adaptation Simulation ESSpi. NN (CSIM) Readout pipeline Cross-val/grid On Implementing Reservoir Computing NIPS 2006 – December 9 5/31
The RC Toolbox: topology Connection structure Rewiring Assign weights Scaling On Implementing Reservoir Computing NIPS 2006 – December 9 6/31
The RC Toolbox: readout Spatial non-linearity Filtering/mean Sp. /temp. non-linearity Scoring On Implementing Reservoir Computing NIPS 2006 – December 9 7/31
The RC Toolbox http: //www. elis. UGent. be/rct On Implementing Reservoir Computing NIPS 2006 – December 9 8/31
Hardware • • Hardware advantages of RC: • Sparse/local connectivity is good • Random weights are allowed • (mild) node and network chaos can be taken advantage of • Weights are fixed or can only change locally with RA Various HW implementations possible: • Spiking/analog/non-linear • Digital/a. VLSI/… On Implementing Reservoir Computing NIPS 2006 – December 9 9/31
Digital spiking neurons • SNN: mathematically a more complex model than ANN • But: better implementable in hardware • No weight multiplications: table look-up • Filtering can be implemented using shifts and adds • Interconnection only single bit, and sparse communication • Asynchronous communication easily implementable On Implementing Reservoir Computing NIPS 2006 – December 9 10/31
Digital spiking neurons • Hardware can take advantage of parallelism • But area-speed trade-off: we don’t have to make the implementation faster than needed by the application • For trade-off: different implementations with other area-speed needed • Possible parallelisms: • • Network parallelism • Neuron/synapse parallelism • Arithmetic parallelism We implemented: • SPPA: network parallel, neuron serial, arithmetic parallel • PPSA: network parallel, neuron parallel, arithmetic serial • SPSA: network serial or parallel, neuron serial, arithmetic serial On Implementing Reservoir Computing NIPS 2006 – December 9 11/31
Digital spiking neurons: PPSA On Implementing Reservoir Computing NIPS 2006 – December 9 12/31
Digital spiking neurons: SPPA On Implementing Reservoir Computing NIPS 2006 – December 9 13/31
Digital spiking neurons: SPSA On Implementing Reservoir Computing NIPS 2006 – December 9 14/31
Results ppsa sppa spsa Number of inputs per neuron On Implementing Reservoir Computing NIPS 2006 – December 9 15/31
Area-speed trade-off for speech task • Speech task in hardware • LSM with 200 neurons • 12 k. Hz processing speed • Real-time requirement LUTs memory SPPA PPSA SPSA 10 PE SPSA 5 PE On Implementing Reservoir Computing NIPS 2006 – December 9 13812 900 kbit 13426 58 kbit 488 144 kbit 489 144 kbit Realtime 347 205 2. 2 1. 1 16/31
Digital spiking neurons and RCT • Topology can be exported from RCT to different HW models • Exploration in SW export to HW for deployment • Basic HW simulation model in RCT On Implementing Reservoir Computing NIPS 2006 – December 9 17/31
Intermezzo: some science • Most valuable resource in hardware: long connections • Impact for RC: readout is hardest part • Solution: only do partial readout • What is performance penalty of this? On Implementing Reservoir Computing NIPS 2006 – December 9 18/31
Intermezzo: some science • Most valuable resource in hardware: long connections • Impact for RC: readout is hardest part • Solution: only do partial readout • What is performance penalty of this? Moore-Penrose pseudo inverse On Implementing Reservoir Computing NIPS 2006 – December 9 19/31
Intermezzo: some science • Most valuable resource in hardware: long connections • Impact for RC: readout is hardest part • Solution: only do partial readout • What is performance penalty of this? Ridge regression Tikhonov regularization Effective parameters On Implementing Reservoir Computing NIPS 2006 – December 9 20/31
Intermezzo: some science • Most valuable resource in hardware: long connections • Impact for RC: readout is hardest part • Solution: only do partial readout • What is performance penalty of this? On Implementing Reservoir Computing NIPS 2006 – December 9 21/31
Future: parallel event based On Implementing Reservoir Computing NIPS 2006 – December 9 22/31
Future: parallel event based On Implementing Reservoir Computing NIPS 2006 – December 9 23/31
Future: parallel event based • Network communication needs to be minimized • Best for networks with much local and few global connections • High speed-up possible due to –Event based –Parallel –Hardware implementation On Implementing Reservoir Computing NIPS 2006 – December 9 24/31
Future: CNN • Cellular Neural/Non-linear Network as reservoir • Outlook: • Very fast, analog non-linear network with only nearest-neighbor connections (128 x 128) • Analog computer: instruction flow possible that implements reservoir and full parallel read-out • Intrinsically random connections: corrections needed when deterministic computations on CNN • Parallel image input via CCD layer • With Samuel Xavier de Souza and Johan Suykens from KULeuven • On ACE 16 k_v 2 chip from Ana. Focus On Implementing Reservoir Computing NIPS 2006 – December 9 25/31
Future: photonic “Photonics is the science and technology of generating, controlling, and detecting photons, particularly in the visible light and near infra-red spectrum“ Wikipedia. org • Currently mainly focused on communication • Long standing photonicist dream: photonic computing • Problems: • Feature size at least order of wavelength (~1μm) • Implementing memory is complex • Change light with light only possible through medium: slow • Laser is intrinsically non-linear/chaotic • Problems with fabrication variances On Implementing Reservoir Computing NIPS 2006 – December 9 26/31
Future: photonic • Possible implementation of reservoir: photonic crystal • Semi-crystal fabricated on silicon to affect the path of light • Creates stop band where light of given bandwidth can’t exist • Light can be bend in any direction • Single crystal ‘flaw’ can be a laser On Implementing Reservoir Computing NIPS 2006 – December 9 27/31
Future: photonic • Idea: use photonics to implement a reservoir • Why: • • Nodes (lasers) intrinsically non-linear/chaotic • Possibly very fast (ps timescale) • Full parallel readout and linear regression trivial • Random (but fixed) process variation is allowed/desired Research project recently started together with Roel Baets and Peter Bienstman from photonics lab at Ghent University On Implementing Reservoir Computing NIPS 2006 – December 9 28/31
Future: photonic LCD LASER On Implementing Reservoir Computing NIPS 2006 – December 9 29/31
Future: photonic • • Possible applications: • Full optical signal reconstruction in optical communication • Optical image processing • Very high speed signal processing Questions/problems: • Harness laser chaos or use it to our advantage • Information in light in multiple physical properties: energy, polarisation, EM field, … On Implementing Reservoir Computing NIPS 2006 – December 9 30/31
Conclusions • The reservoir computing concept is very suited for hardware implementation • … or no … much hardware is very suited to be used as a reservoir On Implementing Reservoir Computing NIPS 2006 – December 9 31/31
- Slides: 31