Talk. Neural Nets: From Rosenblatt's Perceptron to Deep Networks

Conferenciante / Hizlaria: José Ramón Dorronsoro Ibero
Machine Learning Group // Grupo de Aprendizaje Automático.
(Universidad Autónoma de Madrid).

Laburpena / Resumen:
In this talk we will make a review of the evolution and major developments on Neural Networks in the last 60 years, with an emphasis on three concrete models, the early Rosenblatt Perceptron, the Multilayer Perceptron-Backpropagation paradigm of the 90’s and the recent and very successful Deep Networks. For each approach we will discuss its basic properties, successes and stumbling blocks, with the main focus of the presentation being on the models, optimization techniques and technologies underlying the recent boom in Deep Networks.

Eguna / Día: Otsailaren 4a, osteguna / Jueves 4 de Febrero
Ordua / Hora: 16:30 – 18:00
Lekua / Lugar: “Ada Lovelace” aretoan, Informatika Fakultatean / Salón “Ada Lovelace”, Facultad de Informática
Hizkuntza / Idioma: La conferencia será en castellano
Antolatzailea / Organizador: KISA masterra / Máster en Ingeniería Computacional y Sistemas Inteligentes.

Iruzkin bat honentzako: Talk. Neural Nets: From Rosenblatt’s Perceptron to Deep Networks

Erantzuna idatzi

 

 

 

HTML etiketa hauek erabil ditzakezu

<a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>