tinyML Talks: SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers & tinyML doesn’t need Big Data, it needs Great Data

Date

June 9, 2020

Location

Virtual

Contact us

Discussion

Schedule

Timezone: PDT

SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers

Igor FEDOROV, Senior Research Engineer

Arm

The vast majority of processors in the world are actually microcontroller units (MCUs), which find widespread use performing simple control tasks in applications ranging from automobiles to medical devices and office equipment. The Internet of Things (IoT) promises to inject machine learning into many of these every-day objects via tiny, cheap MCUs. However, these resource-impoverished hardware platforms severely limit the complexity of machine learning models that can be deployed. For example, although convolutional neural networks (CNNs) achieve state-of-the-art results on many visual recognition tasks, CNN inference on MCUs is challenging due to severe memory limitations. To circumvent the memory challenge associated with CNNs, various alternatives have been proposed that do fit within the memory budget of an MCU, albeit at the cost of prediction accuracy. This paper challenges the idea that CNNs are not suitable for deployment on MCUs. We demonstrate that it is possible to automatically design CNNs which generalize well, while also being small enough to fit onto memory-limited MCUs. Our Sparse Architecture Search method combines neural architecture search with pruning in a single, unified approach, which learns superior models on four popular IoT datasets. The CNNs we find are more accurate and up to 7.4x smaller than previous approaches, while meeting the strict MCU working memory constraint.

Igor FEDOROV, Senior Research Engineer

Arm

Timezone: PDT

tinyML doesn’t need Big Data, it needs Great Data

Dominic BINKS, VP of Technology

Audio Analytic

Data is the fuel which drives ML. Good quality, realistic, diverse data is essential to train and evaluate tinyML models. Obtaining good quality data, even for something as pervasive as audio, is not as easy as it may seem. This talk will discuss some of the challenges of obtaining and processing good quality audio data for sound recognition tasks and the ways Audio Analytic has overcome those problems.
Topics covered include:

  • what are good sources and bad sources
  • how to gather good quality audio data
  • employing complex labelling strategies
  • using the data to evaluate performance.

While not specially just a tinyML problem, the challenges of running at the edge across disparate devices makes the problem more acute and is shared by other tinyML applications.

Dominic BINKS, VP of Technology

Audio Analytic

Schedule subject to change without notice.