Learning with Azure and Dall-e

 
Spanish Advanced DATA & AI

El Deep Learning no deja de sorprendernos y es por eso que en esta sesión os proponemos ver los últimos avances y el estado del arte del Deep learning. Para ello, utilizaremos como pilar de la sesión uno de los últimos modelos publicados: “Dall-e”, el cual se basa en un modelo de "transformers", siendo capaz de generar imágenes a partir de descripciones de texto. Aquí os dejamos el link donde podeis saber mas del modelo que os estamos comentando: https://openai.com/blog/dall-e/ En esta sesión nos enfocaremos a explicar como se desarrollaría un pipeline de entrenamiento del modelo Dall-e para que aprenda sobre formas geométricas usando varios servicios de Azure. Lo mas importante de todo esto no es solo como se entrena Dalle, si no aprender al mismo tiempo a organizar nuestro proyecto y de como entrenar los modelos de Deep Learning mas actuales en Azure. Para ello utilizaremos Databricks, sera el encargado de gestionar nuestro entrenamiento y validación del modelo, se comentaran el porque y curiosidades del uso de dicho servicio. Se registraran en Azure Machine Learning Service las métricas correspondientes para un modelo de este tipo y se explicaran dichas metricas por consiguiente para entender mejor el porque del modelo seleccionado. Finalmente, el modelo generado y evaluado y que haya pasado nuestros "checks" lo guardaremos en el registro de modelos de Azure Machine Learning Service. Una vez que hayamos entrenado nuestro modelo y haya una versión estable en el registro de Azure Machine Learning, se motrara el componente final para darle uso a dicho modelo. Este ultimo sera un pequeño asistente virtual, haciendo uso de bot framework, el cual ayudará y se comportara como profesor hacia los alumnos para que puedan aprender sobre formas geométricas!

Speakers

Alexander González

AI Software Development Engineer at Plain Concepts | Microsoft Artificial Intelligence MVP

I'm a young entrepreneur, really passionate about technology, Computer vision, Machine and Deep learning engineer. I'm working hard in cloud and AI worlds. Always open to knowledge, to learn, observe, reflect and then to take the best of myself and share it with others. I'm thrilled by the idea of ownership, passionate about creating new AI platforms, features and services from scratch, and thinking about to one day manage the ambiguity and pace of a company shipping software in cycles measured not by years, but by weeks. Lover of AI DevOps and make our intelligent models the capability to deploy everywhere with IoT devices and so interested every time to listen everybody, teachers, developers, geeks, or people who simply are interesting and creative, don't doubt to contact me!

Rodrigo Cabello

AI Technical Lead at Plain Concepts and MVP in Artificial Intelligence

AI Technical Lead and AI MVP at Plain Concepts (Madrid), with an experience of more than 9 years in the development of web applications. He is enthusiastic about new technologies and apps that use techniques based on Artificial Intelligence.

Code of Conduct

We seek to provide a respectful, friendly, professional experience for everyone, regardless of gender, sexual orientation, physical appearance, disability, age, race or religion. We do not tolerate any behavior that is harassing or degrading to any individual, in any form. The Code of Conduct will be enforced.

Who does this Code of Conduct apply to?

All live stream organizers using the Global Azure brand and Global Azure speakers are responsible for knowing and abiding by these standards. Each speaker who wishes to submit through our Call for Presentations needs to read and accept the Code of Conduct. We encourage every organizer and attendee to assist in creating a welcoming and safe environment. Live stream organizers are required to inform and enforce the Code of Conduct if they accept community content to their stream.

Where can I get help?

If you are being harassed, notice that someone else is being harassed, or have any other concerns, report it. Please report any concerns, suspicious or disruptive activity or behavior directly to any of the live stream organizers, or directly to the Global Azure admins at team@globalazure.net. All reports to the Global admin team will remain confidential.

Code of Conduct for local live streams

We expect local organizers to set up and enforce a Code of Conduct for all Global Azure live stream.

A good template can be found at https://confcodeofconduct.com/, including internationalized versions at https://github.com/confcodeofconduct/confcodeofconduct.com. An excellent version of a Code of Conduct, not a template, is built by the DDD Europe conference at https://dddeurope.com/2020/coc/.