go

Ponente: Antonio Manjavacas y Alejandro Campoy Título: Introducción al aprendizaje por refuerzo en Python Aula: Teoría 6 (Sábado) ------------------------------------- Resumen: El aprendizaje por refuerzo es un método de aprendizaje computacional centrado en la interacción de un agente con su entorno. Se trata de un proceso de aprendizaje iterativo, basado en prueba y error, donde el agente recibe recompensas positivas si sus acciones le conducen a estados deseables. Esta rama de la inteligencia artificial, ampliamente ligada a la psicología conductista, ha permitido alcanzar hitos hasta hace poco impensables, como vencer al campeón mundial de Go o StarCraft, dirigir vehículos autónomos, reducir el consumo energético de edificios, o resolver el problema del plegamiento de proteínas: un reto de la biología desde hace más de 50 años. El objetivo de esta charla será ofrecer una introducción práctica al aprendizaje por refuerzo en Python, presentando dos de las librerías más utilizadas en este campo: OpenAI Gym, destinado a la simulación en entornos de aprendizaje, y Stable Baselines, que incluye implementaciones de los algoritmos de aprendizaje por refuerzo que constituyen el estado del arte. Finalmente, estudiaremos una aplicación real del aprendizaje por refuerzo en control energético de edificios, ámbito en el que se enmarca nuestra investigación y últimos trabajos.

We Go One Better Like any great sports team, we’ve put in hard graft since we got going in 1934. It's not by chance we became one of the largest global sports betting and gaming companies, and we're not relying on luck. Together we’re on a journey to build a better business. With us, you’ll balance flexibility and performance in a culture built on trust. We’ll give you the space to be yourself and the tools you need to protect our customers while they play. We’ll invest in your future to help you develop your unique strengths and build a career that’s right for you. Sound good? Then you belong here.

We’re a next-generation SaaS scale-up that builds PIM software for the retail industry. Our name, Plytix, is short for Product Analytics—we started as an ecommerce analytics tool in 2015. Since then, we’ve grown to be one of the leading Product Information Management (PIM) tools. It’s the only PIM system specially made (and priced!) for small to medium-sized ecommerce. It’s a single source of truth that helps teams manage and syndicate product information at scale, allowing you to get your products to market faster and smarter—regardless of the channel. As far as the brains behind the software go, we’re a tight-knit team of passionate, data-driven individuals based here, there, and everywhere in the world! We’re also recognized for our outstanding customer care and employee culture, making us a Great Place To Work in 2021.

Data Architecture Manager at Accenture Born in a town in Seville, Juanjo studied Telecommunications Engineering at the Superior School of Engineering. Since 2004, his professional career has developed at Accenture, working on both national and international development & maintenance projects as Data Engineer and Big Data Engineer. He loves the phrase “If you want to go fast, go alone; if you want to go far, go together.” He likes to help people grow and build teams, loves sports and cooking, and his main hobby is his family. And he is forbidden to give up.

Cuando se quiere llegar a un cierto nivel de rendimiento y paralelismo, se imponen las arquitecturas orientadas a eventos por encima de las APIs síncronas. En esta charla diseñaré y construiré una arquitectura de alto rendimiento utilizando Go y Kafka, mostrando cómo exprimir productores y consumidores para maximizar la eficiencia del sistema.

The Suitcase project is made of a battery-powered suitcase using development boards based on ESP32 microcontrollers Raspberry Pis and a 4G connection and OCI Services. The goal of this project is to enable design and rapid prototyping of stream analysis of events generated by the Suitcase. You will learn how to develop and deploy analytics pipelines that process the events coming from Suitcase and send back the results in case of anomalies and errors.

The remarkable advances in Data, Analytics and AI have fostered a widespread adoption of Machine Learning (ML) capabilities within many products and services we use and consume everyday, ranging from navigation apps up to health-support systems. Nonetheless, implementing ML solutions is still a complex endeavour, and many organizations are struggling to fully exploit the strategic advantages of AI. In this talk, we’ll cover the key concepts that are critical to harness Data & AI leveraging what we have learned from implementing complex software and data-heavy developments in multiple projects. We’ll go through the three stages that we consider when dealing with data products, and we’ll also introduce the principles of Machine Learning Ops (MLOps), a concept that has gained momentum over the last months.

BPMN is often seen as boring ‘Business Speak’. In reality, it is just a way to automate things, and since it’s called the Internet of Things why not automate those things too! With an estimated 75% of IoT deployments failing to deliver on their promises (and 30% dying in the proof of concept phase) it’s clearly time to approach IoT deployments differently. It’s time to design, implement, build and deploy IoT projects from a business perspective rather than a technical standpoint. In this talk I’ll go through a complete IoT solution in 3 iterations to show how Business Process Management platforms can quickly iterate on an IoT solution to deliver maximum benefit. Enough business-speak! I’m going to build a Skittles (candy) dispenser based on IoT and controlled by BPMN, with a little AI thrown in! I’ll run the entire demo live, so if the prospect of watching a demo fail in front of a live audience is what gets you excited, this talk is for you! It’s also for you if you’re struggling to build a business case for your IoT project.

The biggest Google tech event in Spain, carefully crafted for you by GDGMálaga community! Awesome speakers and lots of fun! Do you want to learn how to use Flow (and StateFlow)? Let's use it to create an musical app, to compose together this symphony, applying reactive rhymes and using as base the MVI architecture in Android. In this talk we will share a journey to create a musical app in Android, applying the latest concurrency trends from Kotlin and this beloved reactive Android architecture. We will go from the origins and basics of the architecture, its advantages (and downsides), to the current implementation using the Flow API. #GDGMálaga`22 #DevFestMáalga #BiznagaFest Síguenos en nuestras redes para estar al día de las novedades: - Twitter: https://goo.gl/MU5pUQ - Instagram: https://lk.autentia.com/instagram - LinkedIn: https://goo.gl/2On7Fj/ - Facebook: https://goo.gl/o8HrWX

Distributed systems are inherently complex and exposed to failures in their components. While distributed algorithms try to do their best in handling node and network failures, it is often not possible to mask them. In the presence of failures, systems that thrive for high availability need to allow users to always submit operations and observe the local state (ensuring local-first), leading to potential divergence. Designs with Conflict-free Replicated Data Types (CRDTs) have been used extensively to guarantee that it is possible to converge to a state that reflects concurrent operations. Recent proposals show that it is possible to go beyond state convergence and use CRDTs as a basis for providing additional system-wide guarantees on individual data items, non-negative inc/dec counters, and cross-item guarantees such as referential integrity. This talk introduces the main concepts underpinning CRDTs and these recent proposals.