2024 BrainChip Discussion, page-7844

First 7844 Last

Share
Profile

Follow
manny100

5,664 Posts.

2481

10/08/24

11:33

Post #: 75151521
Share

Originally posted by FullMoonFever: ↑

Nice

Paper HERE

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 through comparison 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 also shown 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

Thanks for that post FMF, clearly shows how superior AKIDA is in our field.

BRN Price at posting: 17.5¢ Sentiment: Buy Disclosure: Held
4 Upvote

0 Great analysis

Reply

Top Stories

ASX Market Update: Index pulls back from record highs | October 16, 2024

BM8

Battery Age Minerals gets set to capitalise on critical mineral demand

JBY

James Bay latest lithium player to pivot to other metals amidst lithium slump

PME

Pro Medicus snaffles 5-year contract extension worth $32M for RIS technology

MKT

The ASX can overlook its Telecomm small-caps. Here’s one diversified brand with an international footprint

There are more pages in this discussion • 2,732 more messages in this thread...

First 7844 Last

Add BRN (ASX) to my watchlist

(20min delay)
Last 24.5¢		Change -0.030(10.9%)		Mkt cap ! $480.8M

Open	High	Low	Value	Volume
26.0¢	27.0¢	24.0¢	$4.928M	19.44M

Buyers (Bids)

No.	Vol.	Price($)
35	1304197	24.5¢

Sellers (Offers)

Price($)	Vol.	No.
25.0¢	839958	18

View Market Depth

No.	Vol.	Price($)
33	1301197	0.245
78	2228316	0.240
39	1426941	0.235
43	796804	0.230
17	1156322	0.225

Price($)	Vol.	No.
0.250	830958	16
0.255	461123	11
0.260	379139	12
0.265	859068	13
0.270	636077	15

Last trade - 16.10pm 16/10/2024 (20 minute delay)

BRN (ASX) Chart

2024 BrainChip Discussion, page-7844

ASX Market Update: Index pulls back from record highs | October 16, 2024

Battery Age Minerals gets set to capitalise on critical mineral demand

James Bay latest lithium player to pivot to other metals amidst lithium slump

Pro Medicus snaffles 5-year contract extension worth $32M for RIS technology

The ASX can overlook its Telecomm small-caps. Here’s one diversified brand with an international footprint

Featured News

Buyers (Bids)

Sellers (Offers)

Featured News

2024 BrainChip Discussion, page-7844

Top Stories

ASX Market Update: Index pulls back from record highs | October 16, 2024

Battery Age Minerals gets set to capitalise on critical mineral demand

James Bay latest lithium player to pivot to other metals amidst lithium slump

Pro Medicus snaffles 5-year contract extension worth $32M for RIS technology

The ASX can overlook its Telecomm small-caps. Here’s one diversified brand with an international footprint

Featured News

Buyers (Bids)

Sellers (Offers)

Featured News