Sign in Subscribe
Artificial intelligence

BrainChip Holdings Ltd to Showcase Edge AI Advancements at Embedded Vision Summit

Strategic Insights

— 1 min read

BrainChip Holdings Ltd, the world's first commercial producer of ultra-low power, fully digital, event-based neuromorphic AI, will participate in the Embedded Vision Summit, taking place May 20-22, 2025, in Santa Clara, CA. Dr. M. Anthony Lewis, the company's Chief Technology Officer, will present a session on the advantages of State-Space Models (SSMs) over traditional Transformer architectures in edge scenarios. The presentation, titled "State-Space Models vs Transformers at the Extreme Edge: Architectural Choices for Low Power AI," will explore the trade-offs and opportunities in designing AI models for environments with severe energy and compute constraints.

Key Takeaways:

  • Dr. M. Anthony Lewis, BrainChip's Chief Technology Officer, will present at the Embedded Vision Summit on the advantages of State-Space Models (SSMs) over traditional Transformer architectures in edge scenarios.
  • The presentation will examine the trade-offs and opportunities in designing AI models for environments with severe energy and compute constraints.
  • SSMs, including BrainChip's proprietary Temporal Event-based Neural Networks (TENNs), offer significant advantages over Transformers in edge scenarios, including reduced total system power and the potential for using novel memory types.
  • The talk will highlight methods for migrating from Transformer-based models like LLaMA to SSMs using distillation, preserving accuracy while dramatically improving efficiency.
  • Attendees of the Summit can visit BrainChip at booth #716 to see live demonstrations of the company's latest advancements in Edge AI technology, including innovations in on-chip language processing, ultra-low power inference, and Akida-powered solutions.
  • BrainChip's participation reinforces its leadership in the rapidly growing field of real-time streaming Edge AI, bringing highly efficient compute to devices in aerospace, automotive, robotics, consumer electronics, and wearables.

Statistics:

  • End date of the Embedded Vision Summit: May 22, 2025
  • Location of the Embedded Vision Summit: Santa Clara, CA
  • Booth number of BrainChip at the Embedded Vision Summit: #716
  • Number of industries that can benefit from BrainChip's Edge AI advancements: 6 (aerospace, automotive, robotics, industrial IoT, consumer devices, and wearables)
  • Name of the AI processor developed by BrainChip: Akida
  • Type of processor developed by BrainChip: Full-digital, event-based neuromorphic processor
  • Advantage of BrainChip's Tenor-based Neural Networks (TENNs): Analyzing only essential sensor inputs at the point of acquisition

Sources:

  • "BrainChip Holdings Ltd (ASX: BRN, OTCQX: BRCHF, ADR: BCHPY)" - BrainChip Holdings Ltd website
  • Embedded Vision Summit - Embedded Vision website
  • Business Wire - "BrainChip Holdings Ltd to Showcase Edge AI Advancements at Embedded Vision Summit"

Read more