My Talks
Some small talking...
Curious about the talks I’ve delivered? Here’s a curated selection of documented sessions where I share insights on data, innovation, and beyond. Each talk includes a video with an introduction to set the stage; just press play and dive in!
This talk, delivered at the Joint Colloquium on Applied Mathematics, explores how artificial intelligence is revolutionizing the food industry, with a focus on product development. I share insights from a research project at ITESO that combines machine learning and optimization techniques to create innovative food products, using data on nutrition, molecular composition, and flavor profiles to shape the future of what we eat.
Artificial intelligence has become an essential tool in many industries, including food innovation. Presented during the Joint Colloquium on Applied Mathematics, this session showcases how AI techniques, such as supervised learning and genetic algorithms, can be applied to design creative, data-driven food products. By leveraging structured datasets containing nutritional properties, molecular composition, and flavor profiles, AI models can generate new and optimized food solutions, offering a glimpse into the future of how we design and experience food.
In this talk, I explore real-world applications of artificial intelligence in the food industry, including a model developed at ITESO to design innovative food products. From supervised learning to genetic algorithms, see how data and creativity come together to shape the future of what we eat.
Artificial intelligence is everywhere today, and it’s here to stay.
However, successfully integrating it into a project requires a clear understanding of which techniques to use and how to apply them effectively. This presentation explores the current applications of AI in the food industry and highlights its impact on new product development. It also showcases how researchers at ITESO have designed an AI model specifically tailored to the food sector. This model learns from structured data, including nutritional properties, molecular composition, and flavor profiles, to generate innovative food products. By integrating machine learning and optimization techniques such as supervised learning and genetic algorithms, AI expands its creative capabilities, offering a glimpse into how this technology is shaping the future of what we eat.
AI Courses (CIANETI)
I had the opportunity to teach intermediate and advanced courses on artificial intelligence through Canieti and TAE, hosted on the PLAI platform. These sessions focused on practical AI applications and advanced techniques, helping participants strengthen their understanding and skills in this rapidly evolving field.
Explainability in AI: Opening the Black Boxes with SHAP and LIME
In this masterclass, delivered for the Data Growth community in Lima, Peru, we explored the critical topic of AI explainability using two key tools: SHAP and LIME.
This session was designed for anyone interested in understanding how AI models work, even without a technical background. We discussed how to make algorithmic behavior more transparent and why explainability is essential for building reliable and ethical AI systems.
Decision-Making with Big Data
I was invited by Grupo Salinas, under Total Play, to participate in the Aprendizaje Total Play campaign. In this talk, I shared how data science tools and Big Data processing can drive informed decision-making by transforming raw information into actionable intelligence.
This session explored the power of Big Data and advanced analytics in improving strategic and operational decisions. By leveraging data science techniques, organizations can extract valuable insights from massive datasets, helping them navigate complexity and act with confidence.
Explaining Machine Learning with SHAP
This talk was delivered at HOY AI CHARLA, organized by Saturdays AI, and focused on improving the interpretability of machine learning models using SHAP.
In the field of data science, machine learning models are often seen as black boxes—systems that take input data and return an output without revealing how decisions are made. This session highlighted the importance of AI model explainability and introduced SHAP as a powerful technique for understanding how input features influence predictions, helping to build more transparent and trustworthy systems.
So, What is NLP?
I was invited to speak at Women in Voice (Mexico) to present an introduction to Natural Language Processing (NLP) and its applications.
In this session, we explored the definition of NLP using a model built with the very same technology. We reviewed key concepts behind these techniques, practical examples of where they are applied, and discussed real-world cases where biased data in NLP models has led to flawed business decisions—highlighting the importance of responsible AI practices.
Explaining Machine Learning Models
I was invited by Women in Data to deliver a series of sessions focused on the explainability of machine learning models.
Across four sessions, we explored various techniques designed to make machine learning models more interpretable. The first session introduced the concept of model explainability and emphasized why it is essential for trustworthy AI. The following sessions took a deeper look at specific techniques—including LIME, ELI5, Anchors, and SHAP—first from a conceptual standpoint and later through hands-on coding examples, demonstrating their practical use in real-world applications.
