Many techniques have been proposed to both accelerate and compress trained Deep Neural Networks (DNNs) for deployment on resource-constrained edge devices. Software-oriented approaches such as pruning and quantization have become commonplace, and several optimized hardware designs have been proposed to improve inference performance. An emerging question for developers is: how can we combine and automate these optimizations together? In this session, we examine a real-world use-case where DNN design space exploration was used with the optimized Ethos-U55 NPU to leverage SW and HW optimizations in one workflow. We will show how to automatically produce optimized TensorFlow Lite CNN model architectures, and speed up the dev-to-deployment process. We’ll present insights from testing Arm’s Vela compiler, FVP and configurable NPU to boost throughput 1.7x and reduce cycle count by 60% for image recognition tasks, enabling complex models typically not available for inference on edge devices. Tech talk resources: https://github.com/Deeplite #ArmDevSummit #Deeplite #MachineLearning
Artificial intelligence is turning into the next industrial revolution, poised to transform business, the global economy and how people work and interact with each other. This has unleashed a debate whether the arrival of human-level AI signals the dawn of paradise, or the sunset of the human race. Will the development of full artificial intelligence enhance our lives, as the technologist Ray Kurzweil argues, or is it “our biggest existential threat,” in the words of Tesla founder Elon Musk, which “could spell the end of the human race,” as astrophysicist Stephen Hawking warns? Will it bring on a new age of human enlightenment, or will it do great harm to society—putting people out of work, adding to inequality and removing warfare from human control, even posing an existential risk to the long-term future of Homo sapiens, replacing humans altogether as a new form of life that outperforms humans? Please join Rabbi Jacobson as he weighs in on this debate and explains how it actually reflects our perspective on the very nature and definition of the human being. The role of AI in our lives compels us to ask some very difficult and challenging questions. Are we machines, which can be replaced by better machines? Or are we more than sophisticated robots? Are our sublime and sensual faculties — like love, soul, imagination, spontaneity and transcendence — uniquely human, or can we program an android with these qualities? Discover that the real power of AI is not its technology, but its [More]