Join Boston Data Science & Data Women on Wednesday, January 17 in Kendall, to hear Alex Wiltschko talk about Tangent, a new open-source Python library developed by the Google Brain team.
This talk is being hosted by Edlitera in Kendall Square.
About the talk
Tangent is a new, free, and open-source Python library for automatic differentiation. In contrast to existing machine learning libraries, Tangent is a source-to-source system, consuming a Python function f and emitting a new Python function that computes the gradient of f. This allows the user to write plain Python code, with native loops and conditionals (like in PyTorch), but benefit from ahead-of-time optimizations (like in TensorFlow). Because Tangent returns pure Python code, this allows much better user visibility into gradient computations, as well as easy user-level editing and debugging of gradients.
About the speaker
Alex Wiltschko is a research scientist at Google Brain, focusing on building more flexible machine learning software systems, and also applications of machine learning to biology. He has helped build the machine learning libraries torch-autograd and Tangent, which are used in both research and production in industry and academia. He completed his PhD in Neurobiology at Harvard, focusing on quantifying behavior and body language using depth cameras and nonparametric time-series modeling.
About the sponsor
Edlitera is a technology company on a mission to help people future-proof themselves by learning the most in-demand and up-to-date skills in programming and data science. We bring Ivy League standards and quality to professional education, and we are the only bootcamp whose courses are being taught in Harvard's lecture halls.