Machine learning and AI

Over the past years I have been exploring how machine learning and AI can be leveraged for materials synthesis and microelectronics.

Evaluating the potential of AI for materials synthesis and manufacturing

Given the wealth of techniques currently available, from traditional machine learning approaches to reasoning large language models, we need to develop a better understanding of how these can be applied to accelerate both process optimization and materials synthesis.

Integrating AI agents with thin film deposition tools

From an experimental standpoint, I am very interested in understanding how to integrate various flavors of AI models with thin film growth techniques and in-situ characterization techniques. My technique of choice so far has been atomic layer deposition, where we have the ability to design custom software to bridge the gap between AI agents built on top of reasoning language models, and the hardware used to control ALD processes.

Exploring how to use AI in conjunction with metrology tools

Can we make the most of the information provided by metrology tools currently used in areas such as semiconductor industry? How much information can we extract from the data that we acquire as part of existing characterization workflows? The use of metrology tools during synthesis and manufacturing is ubiquitous in industry. New methodoloigies can provide information not just about how the current process is doing, but predict how it will perform in different conditions.

Evaluating generative AI for materials synthesis and manufacturing

There is a lot of interest (with a dose of hype) in LLMs and their potential to assist on scientific research. Understanding how state of the art models perform in materials synthesis and processing tasks is something that is critical to determine their usefulness in real life. I am working with a team of domain experts and computer scientists to develop new benchmarks and develop a deeper understanding of their capabilities.

Development of novel algorithms more suitable for materials research

AI and machine learning research tends to look to algorithms that are widely applicable. When someone says that they have applied a blackbox algorithm to a problem, that’s actually a praise. It means that someone has been able to crack a common problem and that the resulting method or algorithm has tons of value.

Conversely, we domain scientists have to deal to very specific constraints or types of data. This means that sometimes we need to adapt existing algorithms or come up with something that is particularized to our needs. The main thing is not that the algorithm is novel, it is that we can now solve a problem that we used to have.

One of the challenges in science is that experiments are really expensive. Developing algorithms that can learn with a few examples and improve as data from other experiments is made available (ideally without the need to go through expensive retraining) is critical to maximize AI’s potential in scientific research. We have been borrowing ideas from many sources, from Gaussian processes to the insect brain to develop continual learning algorithms that target some of our unique challenges in materials synthesis and microelectronics.