Palestra: Automating Software Development with Deep Learning

Track: Machine Learning e Inteligência Artificial

Sala: 2 Nova York

Horário: 10:50am - 11:35am

Dia da semana: Terça-feira

Nível: Intermediário - Avançado

Persona: Cientista de Dados, Desenvolvedor(a) Programador(a), Desenvolvedor(a) Sênior, Gerente de Produto, Gestão (VP, CTO, CIO, Diretoria), Líder Técnico(a)

Apresentação em Inglês

Share this on:

Pontos Principais

  • Software solutions can be replaced with deep learning models that only require a few lines of code;
  • Deep learning models can translate a design mockup into functioning software;
  • Deep learning is making early progress in turning project descriptions into the software;
  • How to obtain a structured output from Deep Learning models.

Resumo

It’s now possible to automate the development of software with deep learning (gradient-based learning of non-linear functions). In areas such as image classification, speech recognition, and self-driving, Deep Learning already generates the majority of the new software. Now it is also starting to make early progress in replacing traditional software, turning design mockups and project descriptions into code. In this presentation I'll cover the state of the art in software development automation, it's current weaknesses, and areas that are ready for production.

Speaker: Emil Wallner

Screenshot-to-code Creator

Emil is a Machine Learning Engineer, currently exploring code and design synthesis, and reinforcement learning. He's studying Computer Science at 42 Paris, where he mentors students on machine learning. In 2018, he made a popular open source project that translates design mock-ups into HTML/CSS, Screenshot-to-code. His blog is translated to a dozen languages, which reaches over a million developers each year. Emil used to work for Oxford's business school and he started an investment firm focussed on education technology.

Find Emil Wallner at

Tracks

Segunda-feira, 6 de maio

Terça-feira, 7 de maio

Quarta-feira, 8 de maio