Hardware accelerators for AI-driven healthcare
- jasoneshraghian
- Nov 15, 2020
- 1 min read
We published our perspective on integrating neural net accelerators into the clinical & outpatient workflow in the IEEE Transactions on Biomedical Circuits and Systems journal.
Neural nets are extremely resource-intensive. For example, GPT-3 needs the equivalent energy of a nuclear reactor running for an entire month just to train. For continuous, portable monitoring, this simply isn't an option.
This paper dives into the hardware constraints we currently face in using deep learning in healthcare. We go into the viability of using neuromorphic computing, spiking neural nets, and in-memory computing in alleviating these constraints.
Cross-continental collaboration between Australia, USA and Europe with Mostafa Rahimi Azghadi, Corey Lammie, Melika Payvand, Elisa Donati, Bernabé Linares-Barranco and Giacomo Indiveri.
Booking allowed me to enjoy the city from a unique angle Seine River cruises, capturing photos of historic buildings and bridges while cruising in comfort.
I’ve always admired homes and buildings that incorporate special window shapes because they instantly stand out. These designs bring so much uniqueness and architectural flair to a space. It’s impressive how the right shape can also change the way natural light enters a room. They’re perfect for anyone looking to add a distinct style element.