Gradient Dissent: AI in Electronics; Quilter's journey in PCB design

Published

June 6, 2024

Written by

Sergiy Nesterenko

Founder and CEO

Read the Full Series

This article is one part of a walkthrough detailing how we recreated an NXP i.MX 8M Mini–based computer using Quilter’s physics-driven layout automation.

Overview: Project Speedrun

Part 1: Preparing the Design

Part 2: Compiling the Design

Part 3: Cleaning Up the Design

Part 4: Testing & Validation

Our CEO Sergiy Nesterenko joins Lukas Biewald on the Weights & Biases podcast to talk about real-world applications of reinforcement learning in PCB design.

00:00 - Introduction to Gradient Dissent
00:45 - Meet Sergiy Nesterenko, CEO of Quilter
01:27 - Understanding PCBs and Their Importance
03:06 - Challenges in PCB Design
08:12 - Automating PCB Layout with AI
10:28 - Physics and Practical Issues in PCB Design
16:07 - Real-World Applications of Quilter
24:13 - Insights on Reinforcement Learning in PCB Design
28:11 - Handling High-Speed PCB Designs
34:22 - Balancing Research and Real-World Applications
38:39 - Challenges and Surprises in Building Quilter
43:25 - Future of PCB Design and AI Integration

Try Quilter for Yourself

Project Speedrun demonstrated what autonomous layout looks like in practice and the time compression Quilter enables. Now, see it on your own hardware.

Get Started

Validating the Design

With cleanup complete, the final question is whether the hardware works. Power-on is where most electrical mistakes reveal themselves, and it’s the moment engineers are both nervous and excited about.

Continue to Part 4

Cleaning Up the Design

Autonomous layout produces a complete, DRC'd design; cleanup is a brief precision pass to finalize it for fabrication.

Continue to Part 3

Compiling the Design

Once the design is prepared, the next step is handing it off to Quilter. In traditional workflows, this is where an engineer meets with a layout specialist to clarify intent. Quilter replaces that meeting with circuit comprehension: you upload the project, review how constraints are interpreted, and submit the job.

Continue to Part 2