![]() ![]() If the sensors can’t detect a green light, human drivers have to take over. Likewise, solar glare can interfere with our traffic light detection software.” In a testing report, first publicized by Xconomy, it said: “In a sense, the challenge for an AV’s sensors resembles the challenge for human drivers: it can be difficult to perceive the state of a traffic light while staring into the sun. NuTonomy, a self-driving car startup that launched a fleet of pilot taxis in Singapore, admitted that sometimes the “low evening sun and solar glare” make it difficult for its cars to see the traffic lights. ![]() Self-driving cars also get blinded by the Sun: Autonomous cars being tested in Boston can’t see the colour of traffic lights due to solar glare. “So, people are trying to design new ways of representing numbers that will be more efficient.” “This might require us to reinvent the way we do arithmetic in circuits,” he said. Smaller models that can fit onto devices like smartphones require cheap accelerators that can perform on the fly. If you want to access it via servers, however, then another type of hardware is needed for data centers. Once the neural network is set in stone, it should run on another chip that doesn’t need as much power and is less expensive. ![]() A chip for training requires rapid speeds so researchers don’t have to wait around for their results, and can tinker with their machine learning code more quickly to finetune the optimum model. LeCun outlines three different types of chips needed for specialised tasks. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |