Featured image: Tesla
The Dojo is a Neural Network (NN) chip being developed by Tesla's hardware team to increase the learning speed of neural networks at the server-side. Tesla CEO Elon Musk said that Dojo V1.0 will be released in about 1 year.
It was first mentioned during Autonomy Day in 2019. Musk said:
"We do have a major program at Tesla which we don't have enough time to talk about today called “Dojo.” That's a super powerful training computer. The goal of Dojo will be to be able to take in vast amounts of data and train at a video level and do unsupervised massive training of vast amounts of video with the Dojo program - or Dojo computer."
Since then, Tesla's CEO has already mentioned the supercomputer several times and has invited people who are interested in its development to join the company's AI team.
Tesla's custom 144 TOPS (Trillion Operations Per Second) in-vehicle inference computer--where almost every TOP is useable & optimized for NN--far exceeds anything else in volume production, given the hardware needed to run sophisticated nets. The dojo will be able to process vast amounts of video training data and efficiently run hyperspace arrays with an extreme number of parameters, plenty of memory & ultra-high bandwidth between cores.
Tesla CEO Elon Musk Recruits AI/Chip Team Members For ‘Dojo’ Supercomputer Developmenthttps://t.co/vR9IJPYNF5— Tesmanian.com (@Tesmanian_com) August 15, 2020
The Dojo is still being built. Musk said there is a lot of work to be done, but technically, Tesla has it working in simulation with FPGAs (Field-Programmable Gate Arrays) at ~ 0.01% capability. Musk said that Version 1.0 could be released in about 1 year.
Dojo is still being built. Maybe a year or so from V1.0.— Elon Musk (@elonmusk) August 15, 2020
FPGA is an integrated circuit designed to be configured by a customer or designer after manufacturing. FPGAs contain an array of programmable logic blocks, and a hierarchy of "reconfigurable interconnects" that allow the blocks to be "wired together," like many logic gates that can be inter-wired in different configurations.
Previously Tesla Autopilot was trapped in a local maximum, labeling single camera images uncorrelated in time, said Musk. He explained that we think of the world in three dimensions (3D), and the fourth dimension (4D) is time. After the company published several patents, it became clear that Tesla was making progress in the transition from operating in 2.5D to operating in 4D.
Compared to your average automaker's driver-assist tech, 4D Autopilot isn't just a game changer: It'll change the entire sport.
© 2020, Eva Fox. All rights reserved.
We appreciate your readership! Please share your thoughts in the comment section below.
About the Author
Eva Fox joined Tesmanian in 2019 to cover breaking news as an automotive journalist. The main topics that she covers are clean energy and electric vehicles. As a journalist, Eva is specialized in Tesla and topics related to the work and development of the company.