报告标题：Mocha.jl – Deep Learning for Julia [Slides]
报告内容：Mocha.jl is an efficient and flexible deep learning framework for Julia, a high-level dynamic language designed specifically for scientific and technical computing. Mocha.jl supports multiple computation backends, including CPUs and GPUs (with CUDA and cuDNN). I will briefly introduce Julia to the potential audience who is not familiar with this new language. After that, I will use an example to illustrate the user interfaces of Mocha.jl and also introduce the design and architecture behind the library implementations.
报告人简介：Chiyuan Zhang received the BS degree and Master degree in Computer Science from Zhejiang University, China, in 2009 and 2012, respectively. He is currently a PhD candidate at Computer Science and Artificial Intelligence Laboratory, MIT, USA. His research interests include machine learning and computational neuroscience, as well as application to processing / analysis of speech, vision and other kinds real-world signals.