Pith. sign in

REVIEW 5 cited by

Theano: A Python framework for fast computation of mathematical expressions

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1605.02688 v1 pith:Q2HTJEC3 submitted 2016-05-09 cs.SC cs.LGcs.MS

Theano: A Python framework for fast computation of mathematical expressions

The Theano Development Team: Rami Al-Rfou , Guillaume Alain , Amjad Almahairi , Christof Angermueller , Dzmitry Bahdanau , Nicolas Ballas , Fr\'ed\'eric Bastien , Justin Bayer
show 104 more authors
Anatoly Belikov Alexander Belopolsky Yoshua Bengio Arnaud Bergeron James Bergstra Valentin Bisson Josh Bleecher Snyder Nicolas Bouchard Nicolas Boulanger-Lewandowski Xavier Bouthillier Alexandre de Br\'ebisson Olivier Breuleux Pierre-Luc Carrier Kyunghyun Cho Jan Chorowski Paul Christiano Tim Cooijmans Marc-Alexandre C\^ot\'e Myriam C\^ot\'e Aaron Courville Yann N. Dauphin Olivier Delalleau Julien Demouth Guillaume Desjardins Sander Dieleman Laurent Dinh M\'elanie Ducoffe Vincent Dumoulin Samira Ebrahimi Kahou Dumitru Erhan Ziye Fan Orhan Firat Mathieu Germain Xavier Glorot Ian Goodfellow Matt Graham Caglar Gulcehre Philippe Hamel Iban Harlouchet Jean-Philippe Heng Bal\'azs Hidasi Sina Honari Arjun Jain S\'ebastien Jean Kai Jia Mikhail Korobov Vivek Kulkarni Alex Lamb Pascal Lamblin Eric Larsen C\'esar Laurent Sean Lee Simon Lefrancois Simon Lemieux Nicholas L\'eonard Zhouhan Lin Jesse A. Livezey Cory Lorenz Jeremiah Lowin Qianli Ma Pierre-Antoine Manzagol Olivier Mastropietro Robert T. McGibbon Roland Memisevic Bart van Merri\"enboer Vincent Michalski Mehdi Mirza Alberto Orlandi Christopher Pal Razvan Pascanu Mohammad Pezeshki Colin Raffel Daniel Renshaw Matthew Rocklin Adriana Romero Markus Roth Peter Sadowski John Salvatier Fran\c{c}ois Savard Jan Schl\"uter John Schulman Gabriel Schwartz Iulian Vlad Serban Dmitriy Serdyuk Samira Shabanian \'Etienne Simon Sigurd Spieckermann S. Ramana Subramanyam Jakub Sygnowski J\'er\'emie Tanguay Gijs van Tulder Joseph Turian Sebastian Urban Pascal Vincent Francesco Visin Harm de Vries David Warde-Farley Dustin J. Webb Matthew Willson Kelvin Xu Lijun Xue Li Yao Saizheng Zhang Ying Zhang
This is my paper
classification cs.SC cs.LGcs.MS
keywords theanosectionbeenlearningmachinemathematicalcommunitycompares
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially in the machine learning community - and has shown steady performance improvements. Theano is being actively and continuously developed since 2008, multiple frameworks have been built on top of it and it has been used to produce many state-of-the-art machine learning models. The present article is structured as follows. Section I provides an overview of the Theano software and its community. Section II presents the principal features of Theano and how to use them, and compares them with other similar projects. Section III focuses on recently-introduced functionalities and improvements. Section IV compares the performance of Theano against Torch7 and TensorFlow on several machine learning models. Section V discusses current limitations of Theano and potential ways of improving it.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. The JWST Search for Earth-Luna Analogs: Upper Limits on Exomoons and Refined Ephemerides for TOI 700 d and e

    astro-ph.EP 2026-04 conditional novelty 7.0

    JWST transit observations refine ephemerides of TOI 700 d and e by an order of magnitude in period precision but yield only upper limits on exomoons larger than Ganymede due to 46 ppm correlated noise attributed to st...

  2. PyTorch: An Imperative Style, High-Performance Deep Learning Library

    cs.LG 2019-12 accept novelty 7.0

    PyTorch demonstrates compatibility of imperative Pythonic usability with high performance and accelerator support through its runtime architecture and benchmark results.

  3. Uniform Metallicity Measurements of M Dwarf Planet Hosts Support Metallicity-Dependent Sub-Neptune Formation

    astro-ph.EP 2026-07 conditional novelty 6.0

    Homogeneous SpeX metallicities of M-dwarf planet hosts show sub-Neptune hosts are more metal-rich than super-Earth hosts, supporting ice-line formation plus migration.

  4. Learning to Reformulate the Queries on the WEB

    cs.IR 2019-07 unverdicted novelty 5.0

    An unsupervised character-level CNN encoder with attention-based RNN decoder, trained on Clueweb09 anchor phrases, generates query reformulations that improve retrieval on TREC collections.

  5. Peering through the disc of HD 98800 BaBb. Precise timing predictions for the HD 98800 AaAb occultation

    astro-ph.EP 2026-07 conditional novelty 4.0

    New RVs and multi-wavelength astrometry tighten the HD 98800 outer orbit by ~2×, yielding 5–15-day 1σ windows for the 2025–2031 disc occultation of AaAb.