• Publications
  • Influence
Theano: A Python framework for fast computation of mathematical expressions
TLDR
The performance of Theano is compared against Torch7 and TensorFlow on several machine learning models and recently-introduced functionalities and improvements are discussed.
Theano: A CPU and GPU Math Compiler in Python
TLDR
This paper illustrates how to use Theano, outlines the scope of the compiler, provides benchmarks on both CPU and GPU processors, and explains its overall design.
Theano: Deep Learning on GPUs with Python
TLDR
This paper presents Theano, a framework in the Python programming language for defining, optimizing and evaluating expressions involving high-level operations on tensors, and adds automatic symbolic differentiation, GPU support, and faster expression evaluation.
Quickly Generating Representative Samples from an RBM-Derived Process
TLDR
This work extends FPCD using an idea borrowed from Herding in order to obtain a pure sampling algorithm, which it is called the rates-FPCD sampler, which can improve the model as the authors collect more samples, since it optimizes a lower bound on the log likelihood of the training data.
Automatic differentiation in ML: Where we are and where we should be going
TLDR
A new graph-based intermediate representation (IR) is introduced which specifically aims to efficiently support fully-general AD for array programming, and naturally supports function calls, higher-order functions and recursion, making ML models easier to implement.
Automatic Differentiation in Myia
TLDR
This work implements a first-order gradient operator for a subset of the Python programming language, building on the work by Pearlmutter and Siskind and attempting to have the best of both worlds.
Automatic Differentiation in Myia Extended Abstract
TLDR
This work implements a first-order gradient operator for a subset of the Python programming language, building on the work by Pearlmutter and Siskind and attempting to have the best of both worlds.