TinyMM: Multimodal-Multitask Machine Learning on Low-Power MCUs for Smart Glasses.
Lokmane DemaghPatrick GardaCédric GilbertKhalil HachichaPublished in: SENSORS (2023)
Keyphrases
- low power
- multi task
- machine learning
- learning tasks
- low cost
- power consumption
- high speed
- learning problems
- multitask learning
- transfer learning
- multi task learning
- feature selection
- single chip
- supervised learning
- vlsi architecture
- vlsi circuits
- machine learning algorithms
- learning algorithm
- digital signal processing
- multiple tasks
- multi class
- gaussian processes
- cmos technology
- logic circuits
- low power consumption
- kernel methods
- learning experience
- information extraction
- computer vision
- image sensor
- unsupervised learning
- natural language processing
- support vector machine
- reinforcement learning
- mixed signal
- gate array
- inductive learning
- multi label
- decision trees