Media Videos – Perceive

[Embedded Vision Summit] Generative AI: How will it impact edge applications and machine perception?

Perceive CEO Steve Teig joined Sally Ward-Foxton, Senior Reporter at EE Times, and a panel of experts for this general session at Embedded Vision Summit in May. This lively and insightful panel discussion focuses on the rapidly evolving role of generative AI in edge and machine perception applications.

[Edge AI + Vision Alliance] “Making GANs Much Better, or If at First You Don’t Succeed, Try, Try a GAN,” a Presentation from Perceive

For the full version of this video, please visit https://www.edge-ai-vision.com/2023/07/making-gans-much-better-or-if-at-first-you-dont-succeed-try-try-a-gan-a-presentation-from-perceive/. (Free with site registration.)

[Edge AI + Vision Alliance] Perceive Demonstration of Image Classification and Pose Detection using Ergo AI Processors

At the Edge AI + Vision Alliance Innovation Forum, Perceive VP of Marketing, David McIntyre shows off the capabilities of the Ergo 2 chip, running 17-key-point pose detection, using two neural networks at the same time but still operating at very low power.

[Synopsis] Perceive Ergo SoC with ARC Processor & Security IP

Watch the video to see how Perceive Ergo SoC with integrated Synopsys ARC Processor and Security IP delivers high-performance computing with ultra-low power for edge devices.

[AI Compute Symposium 2022] Machine learning for real: Thinking more carefully about efficiency, loss functions, and GANs

Today’s deep learning relies heavily on folklore: on recipes and anecdotes, rather than on scientific principles and explanatory mathematics. Our CEO, Steve Teig, considers how much more trustworthy, robust, compact, and power-efficient our models would be if we designed them more rigorously.

[Design Automation Conference 2022] Keynote: Machine Learning for Real – Why Principles, Efficiency, and Ubiquity Matter

In this keynote address, Perceive CEO Steve Teig will discuss how deep learning’s reliance on inefficient models based on recipes and anecdotes, rather than scientific principles and explanatory mathematics, leads to unsustainable compromises in power-efficiency, privacy, and user experience.

[Embedded Vision Summit 2022] “Facing Up to Bias,” a Presentation from Perceive

At the Embedded Vision Summit, Perceive CEO Steve Teig spoke about the issues around poor statistical reasoning that contribute to these biased results, and explored how models can be trained in ways that can mitigate bias.

[Embedded Vision Summit 2022] “TinyML Isn’t Thinking Big Enough,” a Presentation from Perceive

In this presentation from Embedded Vision Summit 2021, Steve Teig explores how TinyML can be harnessed to revolutionize the future of machine learning, even outside of the realm of microcontrollers.

[Embedded Vision Summit 2022] “Accuracy: Beware of Red Herrings and Black Swans,” a Presentation from Perceive

Steve Teig, CEO of Perceive, presents the “Accuracy: Beware of Red Herrings and Black Swans” tutorial at the September 2020 Embedded Vision Summit.

[Embedded Vision Summit 2022] “The Opportunities and Challenges in Realizing the Potential for AI at the Edge: An Update from the Front Lines,” An Embedded Vision Summit Expert Panel Discussion

Samir Kumar, Managing Director at Microsoft M12, moderates the “Opportunities and Challenges in Realizing the Potential for AI at the Edge: An Update from the Front Lines” Expert Panel at the September 2020 Embedded Vision Summit.

[Embedded Vision Summit 2020] Perceive’s Steve Teig Describes How to Do Data Center-Class Inference in Edge Devices at Low Power

Steve Teig, CEO of Perceive, presents the “Ergo: Perceive’s Chip – Data Center-Class Inference in Edge Devices at Ultra-Low Power” tutorial at the September 2020 Embedded Vision Summit.