BRN (ASX) 2024 BrainChip Discussion

Originally posted by FullMoonFever: ↑

Nice

PaperHERE

Submitted on 21 Jul 2024]
Few-Shot Transfer Learning for Individualized Braking Intent Detection on Neuromorphic Hardware
Nathan Lutes,Venkata Sriram Siddhardh Nadendla,K. Krishnamurthy

Objective: This work explores use of a few-shot transfer learning method to train and implement a convolutional spiking neural network (CSNN) on a BrainChip Akida AKD1000 neuromorphic system-on-chip for developing individual-level, instead of traditionally used group-level, models using electroencephalographic data. The efficacy of the method is studied on an advanced driver assist system related task of predicting braking intention. Main Results: Efficacy of the above methodology to develop individual specific braking intention predictive models by rapidly adapting the group-level model in as few as three training epochs while achieving at least 90% accuracy, true positive rate and true negative rate is presented.Further, results show an energy reduction of over 97% with only a 1.3x increase in latency when using the Akida AKD1000 processor for network inference compared to an Intel Xeon CPU. Similar results were obtained in a subsequent ablation study using a subset of five out of 19 channels.

Significance: Especially relevant to real-time applications, this work presents an energy-efficient, few-shot transfer learning method that is implemented on a neuromorphic processor capable of training a CSNN as new data becomes available, operating conditions change, or to customize group-level models to yield personalized models unique to each individual.

5. Conclusion
The results show that the methodology presented was effective to develop individual-level models deployed on a state-of-the-art neuromorphic processor with predictive abilities for ADAS relevant tasks, specifically braking intent detection.

This study explored a novel application of deep SNNs to the field of ADAS using a neuromorphic processor by creating and validating individual-level braking intent classification models with data from three experiments involving pseudo-realistic conditions. These conditions included cognitive atrophy through physical fatigue and real-time distraction
and providing braking imperatives via commonly encountered visual stimulus of traffic lights. The method presented demonstrates that individual-level models could be quickly created with a small amount of data, achieving greater than 90% scores across all three classification performance metrics in a few shots (three epochs) on average for both the ACS and FCAS. This demonstrated the efficacy of the method for different participants operating under non-ideal conditions and using realistic driving cues and further suggests that a reduced data acquisition scheme might be feasible in the field.
Furthermore, the applicability to energy-constrained systems was demonstrated throughcomparison of the inference energy consumed with a very powerful CPU in which the Akida processor offered energy savings of 97% or greater. The Akida processor was alsoshown to be competitive in inference latency compared to the CPU.Future work could
include implementation of the method presented on a larger number of participants, other neuromorphic hardware, different driving scenarios, and in real-world scenarios where individual-level models are created by refining previously developed group-level models in real time.

Expand

Further to the paper I posted a couple of weeks ago, this is one of the authors presenting and discussing the work including the use of Akida.

Gives some good insight into how beneficial neuromorphic will be and how being such a recent field in the scheme of technology development the additional work needed to develop models and algos to fully realise its potential.

Like most nascent tech, it's not just a plug and play gig that some seem to think, but takes time to develop the additional external framework & inputs that need to go with it rather than what's been used for last x decades.

No.	Vol.	Price($)
50	1281949	17.5¢

No.

Vol.

Price($)

1281949

17.5¢

Price($)	Vol.	No.
18.0¢	202676	8

Price($)

Vol.

No.

18.0¢

202676

No.	Vol.	Price($)
49	1276949	0.175
82	2768435	0.170
55	2675316	0.165
69	1267060	0.160
25	1061772	0.155

No.

Vol.

Price($)

1276949

0.175

2768435

0.170

2675316

0.165

1267060

0.160

1061772

0.155

Price($)	Vol.	No.
0.180	202676	8
0.185	828566	10
0.190	813900	21
0.195	948924	17
0.200	996514	43

Price($)

Vol.

No.

0.180

202676

0.185

828566

0.190

813900

0.195

948924

0.200

996514

(20min delay)
Last 17.5¢		Change -0.005(2.78%)		Mkt cap ! $342.8M

Open	High	Low	Value	Volume
18.5¢	18.5¢	17.5¢	$692.6K	3.851M

2024 BrainChip Discussion, page-8159

Banking on ANZ in this week's Hot Stock tips

Chariot locks in high-potential drill target at Black Mountain, one of the USA's largest lithium landholdings

UNITH hard launching AI 'digital human' platform too 600+ companies as AI thematic survives sell-off

'Joaquin Silver District' acquisition to become a key asset for Unico

Ingenia shares jump 7% on strong revenue and earnings figures

Featured News

Buyers (Bids)

Sellers (Offers)

Featured News

2024 BrainChip Discussion, page-8159

Top Stories

Banking on ANZ in this week's Hot Stock tips

Chariot locks in high-potential drill target at Black Mountain, one of the USA's largest lithium landholdings

UNITH hard launching AI 'digital human' platform too 600+ companies as AI thematic survives sell-off

'Joaquin Silver District' acquisition to become a key asset for Unico

Ingenia shares jump 7% on strong revenue and earnings figures

Featured News

Buyers (Bids)

Sellers (Offers)

Featured News