Theano: A Python framework for fast computation of mathematical expressions
Explore this paper's citation graph
Summary
The performance of Theano is compared against Torch7 and TensorFlow on several machine learning models and recently-introduced functionalities and improvements are discussed.
- Type
- preprint
- Published
- 2016-05-09
- Cited by
- 2,380
- References
- 34
- Access
- Open access
- OpenAlex
- https://openalex.org/W2384495648
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:8993325
Keywords
Python (programming language), Computer science, Compiler, Computation, Section (typography)
References
- Torch7: A Matlab-like Environment for Machine Learning
- Lasagne: First release.
- Describing Videos by Exploiting Temporal Structure
- Recurrent Neural Network Regularization
- One weird trick for parallelizing convolutional neural networks
- Theano: new features and speed improvements
- cuDNN: Efficient Primitives for Deep Learning
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Pylearn2: a machine learning research library
- Fast Exact Multiplication by the Hessian
- Going deeper with convolutions
- Blocks and Fuel: Frameworks for deep learning
- The NumPy Array: A Structure for Efficient Numerical Computation
- Caffe: Convolutional Architecture for Fast Feature Embedding
- ImageNet classification with deep convolutional neural networks
- Large Scale Distributed Deep Networks
- MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
- Probabilistic programming in Python using PyMC3
- Theano: Deep Learning on GPUs with Python
- Virtualizing Deep Neural Networks for Memory-Efficient Neural Network Design
Cited by
- Automatic Optimization of the Computation Graph in the Nengo Neural Network Simulator
- Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules
- Learning from data to predict future symptoms of oncology patients
- eToxPred: a machine learning-based approach to estimate the toxicity of drug candidates
- Convolutional Mixture of Experts Model: A Comparative Study on Automatic Macular Diagnosis in Retinal Optical Coherence Tomography Imaging
- Gaze bias differences capture individual choice behaviour
- A Deep Neural Network for Predicting and Engineering Alternative Polyadenylation
- Big Learning with Bayesian Methods
- Semi-supervised Learning with Encoder-Decoder Recurrent Neural Networks: Experiments with Motion Capture Sequences
- Value Iteration Networks
- RATM: Recurrent Attentive Tracking Model
- Practical Black-Box Attacks against Deep Learning Systems using Adversarial Examples
- Architectural Complexity Measures of Recurrent Neural Networks
- Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus
- A Fast Unified Model for Parsing and Sentence Understanding
- A Character-level Decoder without Explicit Segmentation for Neural Machine Translation
- Visualization Regularizers for Neural Network based Image Recognition
- LSTM with working memory
- Ristretto: Hardware-Oriented Approximation of Convolutional Neural Networks
- A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues