A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays

In the last few years, research and development on Deep Learning models & techniques for ultra-low-power devices - in a word, TinyML - has mainly focused on a train-then-deploy assumption, with static models that cannot he adapted to newly collected data without cloud-based data collection and fine-tuning. Latent Replay-based Continual Learning (CL) techniques (Pellegrini et al, 2020) enable online, serverless adaptation in principle, but so far they have still been too computation- and memory-hungry for ultra-low-power TinyML devices, which are typically based on microcontrollers. In this work, we introduce a HW/SW platform for end-to-end CL based on a 10-core FP32-enabled parallel ultra-low-power (PULP) processor. We rethink the baseline Latent Replay CL algorithm, leveraging quantization of the frozen stage of the model and Latent Replays (LRs) to reduce their memory cost with minimal impact on accuracy. In particular, 8-bit compression of the LR memory proves to be almost lossless (-0.26% with 3000LR) compared to the full-precision baseline implementation, but requires 4x less memory, while 7-bit can also be used with an additional minimal accuracy degradation (up to 5%). We also introduce optimized primitives for forward and backward propagation on the PULP processor, together with data tiling strategies to fully exploit its memory hierarchy, while maximizing efficiency. Our results show that by combining these techniques, continual learning can be achieved in practice using less than 64MB of memory - an amount compatible with embedding in TinyML devices. On an advanced 22nm prototype of our platform, called VEGA, the proposed solution performs on average 65 x faster than a low-power STM32 L4 microcontroller, being 37 x more energy efficient - enough for a lifetime of 535h when learning a new mini-batch of data once every minute.