Together with selected hardware partners, Robovision AI offers a proven end-to-end solution for Automatic Defect Classification (ADC) in the semiconductor wafer-production process. Here are the top 3 reasons why data teams in semicon love to work with us.
1. Your operators become AI creators
With our platform, you don’t need to be an AI specialist to create AI. Perform every step of the AI life cycle, without ever encountering a line of code. This way, domain experts and business users can contribute their knowledge and help develop better AI, without having to understand the ins and outs of it.
2. Streamline recipe creation with AI-ADC
Advanced integrated circuit semiconductors consist of hundreds of layers. Each of these wafer layers requires a new model based on a unique dataset. Our specialised algorithm enables automated wafer-map pattern classification, eliminating the need to train the algorithm for each layer. That translates to a faster time to market and the fast switching of production lines.
3. AI to production with a single platform
Training an AI model is just the beginning. Maintaining them and monitoring their performance is actually the hard part. Our Robovision AI platform manages the entire AI lifecycle and makes every step as smooth and intuitive as possible, from data management to model deployment.
The go-to platform for the world’s most demanding semicon manufacturers
Hitachi has one of the most diverse product portfolio’s in the entire semiconductor industry. This diversity proved very challenging for their quality insurance, since this requires both an easily retrainable and an ultra-reliable classification system. We are proud they chose the Robovision platform for their ADC classification.
Customised AI Algorithm & Award-winning User Interface
Start delivering AI solutions in time and within budget by using a platform that does the hard work for you. Count on a specialised semiconductor algorithm to reliably do defect classification for a broad variety in patterns. And have your operators train the platform without hiring expensive data-scientists.