Two tinyML Talks on July 7, 2020 by Zuzana Jelcicova from Demant and Daniel Situnayake from Edge Impulse

We held our tenth tinyML Talks webcast with two presentations: Zuzana Jelcicova from Demant has presented Benchmarking and Improving NN Execution on Digital Signal Processor vs. Custom Accelerator for Hearing Instruments and Daniel Situnayake from Edge Impulse has presented How to train and deploy tiny ML models for three common sensor types on July 7, 2020 at 8:00 AM and 8:30 AM Pacific Time.

Zuzana Jelcicova (left) and Daniel Situnayake (right)

Hearing instruments are supported by multicore processor platforms that include several digital signal processors (DSPs). These resources can be used to implement neural networks (NNs); however, execution time and energy consumption are prohibitive to do so. In this presentation, we will talk about benchmarking neural network workloads relevant for hearing aids on Demant’s DSP-based platform. We will also introduce a custom NN processing engine (NNE) that was developed to achieve further power optimizations by exploiting a set of various techniques (reduced wordlength, several MACs in parallel, two-step scaling etc.).
A pretrained, fully connected feedforward NN (Hello Edge: Keyword Spotting on Microcontrollers) was used as a benchmark model to run a keyword spotting application using Google speech command dataset on both, the DSP and NNE. We will talk about the performance of the two implementations, where the NNE significantly outperforms the DSP solution.

Zuzana Jelcicova graduated from Technical University of Denmark (DTU) in 2019 as a MSc of Computer Science and Engineering. Since then she has been pursuing a Ph.D. degree in collaboration with DTU and Demant A/S - an international hearing healthcare group that offers solutions and services to help people with hearing loss. The topic of Zuzana’s Ph.D. are neural networks in resource constraint hearing instruments with the focus on hardware and digital design.

TinyML is incredibly exciting, but if you’re hoping to train your own model it can be difficult to know where to start. In this talk, Dan walks through his workflow and best practices for training models for three very different types of data: time-series from sensors, audio, and vision. We’ll be using Edge Impulse, a free online studio for training embedded machine learning models.

Daniel Situnayake is the Founding TinyML engineer at Edge Impulse. He’s co-author of the O’Reilly book TinyML, alongside Pete Warden. He previously worked on the TensorFlow team at Google, and he co-founded Tiny Farms Inc., deploying machine learning on industrial scale insect farms.


Watch on YouTube:
Zuzana Jelcicova
Daniel Situnayake

Download presentation slide:
Zuzana Jelcicova
Daniel Situnayake

Feel free to ask your questions on this thread and keep the conversation going!

Are the questions from the talks going to be posted here? I had a question for Dan regarding the way the collected data is handled by Edge Impulse in terms of how confidentiality of data is handled. Does Edge Impulse support GDPR data removals tasks for example?

Hi Dominic,

Thanks for your question. We do not allow collection of PII in datasets by our terms of service, thus GDPR is not relevant there. Regardless, datasets are owned by our users and are confidential, and they can remove data at any time. We do not share user datasets or user data. We apply GDPR to our user logins and newsletter mail lists.