Hi Forrest,Hi @Diogenese and @factfinder @uiux and any other long termer.
Have there been any previous dots connecting Brainchip with Logitech? I don’t recall reading anything.
I was trolling through Rob Telson’s Linkedin account and he ‘liked’ a Logitech product:
Logitech announces Sight, an AI-powered tabletop camera for Hybrid Meetings
I know a ‘random’ like by itself doesn’t mean anything. Who knows, maybe he ‘liked’ it because he wants to buy one for the office to help facilitate zoom meetings.
However, I came across an article from October 2019 co-written by Giorgia Dellaferrera of IBM and Miloš Cerňak of Logitech.
The article discusses the validity of using SNN architecture for VAD (Voice Activity Detection system). It references Loihi on a few occasions but no reference to AKIDA.
This is the conclusion:
4. CONCLUSION We propose a SNN architecture for VAD. We developed a novel method for encoding the filterbank single frame features into spike patterns. We next integrated the new encoding scheme into a simple bilayer architecture which we evaluated on the QUT-NOISE-TIMIT data set. We showed that exploiting the power-efficiency properties of SNNs enables the design of VAD systems working at constant low power and achieving performances comparable to the state-of-the art methods. Our framework exhibits a low latency and relies on relatively small training data.
file:///C:/Users/g_rho/Downloads/A_Bin_Encoding_Training_of_a_Spiking_Neural_Networ.pdf
In another article she writes about SNN and back-propogation, so I don’t think she was using AKIDA. I haven’t found any connection to Brainchip but was curious if Logitech may have seen the light and started using AKIDA in the past 2 years. I’m wondering if there is any significance to Rob’s ‘like’, SNN, and Logitech. Are there any patents from Logitech using SNN?
I would appreciate any insights. Thanks in advance.
Logitech have seveeral NN patents/applications. This one seems to relate to the table camera:
US10965908B1 Advanced video conferencing systems and methods
Priority 2020
The advanced single camera video conferencing system features a hybrid optical/digital camera, herein a camera device, having a controller that is configured to execute one or more of the methods set forth herein. In one embodiment, a method includes optically framing, a first portion of a video conferencing environment to provide an actual field-of-view, digitally framing a second portion of the video conferencing environment to provide an apparent field-of-view that is encompassed within the actual field-of-view, generating a video stream of the apparent field-of-view, surveying the actual field-of-view to generate survey data, and detecting changes in the survey data over time. The method may be performed using a single camera device using a single image sensor.
[0070] At activity 345 , the method 300 includes analyzing each of the plurality of survey frames to generate survey data 228 . Analyzing the survey frames may include using a software application 224 executing on the processor 212 to detect and/or recognize conference participants located within the actual field-of-view, e.g., by use of convolutional neural network.
They have 3 other patents with the same title so they probably cover different inventive features.
They also have a couple of dozen other patents in the NN field:
https://worldwide.espacenet.com/pat...5908B1?q=pa = "logitech" AND nftxt = "neural"
While the power may not be a problem, the CNN latency may be.
I believe that there is now a SNN SoC which can run CNN and native SNN at very low power, high accuracy and real time.