PerformanceStar

PerformanceStar is a well-funded contract research and development company based in Santa Clara, California. The company specializes in developing high-performance big-data analysis and machine learning technologies tailored for the semiconductor industry. PerformanceStar focuses on creating smart machine learning applications using a variety of advanced technologies, including evolutionary computing, clustering, support vector machines, decision trees, wavelets, FFTs, DCT, Bayes’ nets, complex event processing, optimization algorithms, pattern recognition, and image analysis.

PerformanceStar builds R&D prototypes that evolve into mission-critical applications for its customers. These prototypes and applications address complex problems such as diagnosing and correcting equipment performance issues, learning and differentiating between normal and abnormal equipment behavior, comparing equipment performance, identifying critical sensor variables, and optimizing overall performance. One of their notable projects, Meta-Learning, aims to automate significant parts of the machine learning configuration and usage process.

The company utilizes a tool called Equipment Health Monitor (EHM) to monitor arbitrary sensor streams and detect unexpected behaviors in real-time. EHM is deployed to monitor hundreds of sensors in semiconductor manufacturing tools. Additionally, PerformanceStar works on computer vision and analytics for stem cell production, focusing on induced pluripotent stem cells for applications like fundamental research, curing diseases, tissue and organ replacement, and personalized drug testing. They mine large datasets, including enzyme, metabolome, medium concentration, karyotype, and image data, to advance stem cell research.

PerformanceStar employs a range of machine learning techniques, from unsupervised to supervised and reinforcement learning, including regression and classification, to assess stem cell quality and differentiation capability. The company seeks individuals with strong backgrounds in Machine Learning, Computer Science, Statistics, Mathematics, Computer Vision, Image Processing, Data Mining, Data Visualization, and Database Management.