Blocks and Fuel: Frameworks for deep learning

We introduce two Python frameworks to train neural networks on large datasets: Blocks and Fuel. Blocks is based on Theano, a linear algebra compiler with CUDA-support (Bastien et al., 2012; Bergstra et al., 2010). It facilitates the training of complex neural network models by providing parametrized Theano operations, attaching metadata to Theano’s symbolic computational graph, and providing an extensive set of utilities to assist training the networks, e.g. training algorithms, logging, monitoring, visualization, and serialization. Fuel provides a standard format for machine learning datasets. It allows the user to easily iterate over large datasets, performing many types of pre-processing on the fly.

• Publication year

  2015

• Venue

  arXiv.org

• Publication date

  2015-06-01

• Fields of study

  Mathematics, Computer Science

• Identifiers
  arXiv 1506.00619
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Deep Learning

  2016cited by this paper
• DRAW: A Recurrent Neural Network For Image Generation

  2015cited by this paper
• Neural Machine Translation by Jointly Learning to Align and Translate

  2014cited by this paper
• Pylearn2: a machine learning research library

  2013cited by this paper
• Maxout Networks

  2013cited by this paper
• Theano: new features and speed improvements

  2012cited by this paper
• On the difficulty of training recurrent neural networks

  2012cited by this paper

• An Integrated Framework of Two-Stream Deep Learning Models Optimal Information Fusion for Fruits Disease Recognition

  2024cites this paper
• Binary swallow swarm optimization with convolutional neural network brain tumor classifier for magnetic resonance imaging images

  2023cites this paper
• Deep Learning for Natural Language Processing: A Survey

  2023cites this paper
• Unveiling the frontiers of deep learning: Innovations shaping diverse domains

  2023cites this paper
• A Simple Translation System Using a Machine Learning Algorithm

  2023cites this paper
• A new optimal prediction technique for energy demand based on CNN and improved water strider algorithm: a study on socio-economic-climatic parameters

  2022cites this paper
• PredicTF: prediction of bacterial transcription factors in complex microbial communities using deep learning

  2022cites this paper
• Deeply learned preselection of Higgs dijet decays at future lepton colliders

  2022influential citation
• Auto-Threshold Deep SVDD for Anomaly-based Web Application Firewall

  2021cites this paper
• VeHIF: An Accessible Vegetation High-Impedance Fault Data Set Format

  2021cites this paper
• PredicTF: a tool to predict bacterial transcription factors in complex microbial communities

  2021cites this paper
• Implementing graph neural networks with TensorFlow-Keras

  2021cites this paper
• Deep Learning for Misinformation Detection on Online Social Networks: A Survey and New Perspectives

  2021cites this paper
• COVID-19 Diagnosis from CT Images with Convolutional Neural Network Optimized by Marine Predator Optimization Algorithm

  2021cites this paper
• Optimal brain tumor diagnosis based on deep learning and balanced sparrow search algorithm

  2021cites this paper
• Novel computer‐aided lung cancer detection based on convolutional neural network‐based and feature‐based classifiers using metaheuristics

  2021cites this paper
• A Method for Optimal Detection of Lung Cancer Based on Deep Learning Optimized by Marine Predators Algorithm

  2021cites this paper
• Plug and Play, Model-Based Reinforcement Learning

  2021influential citation
• DeepRank: a deep learning framework for data mining 3D protein-protein interfaces

  2021cites this paper
• Deep learning for misinformation detection on online social networks: a survey and new perspectives

  2020cites this paper
• DeepDCA: Novel Network-Based Detection of IoT Attacks Using Artificial Immune System

  2020cites this paper
• Back-analysis for initial ground stress field at a diamond mine using machine learning approaches

  2020cites this paper
• The Roles of Language Models and Hierarchical Models in Neural Sequence-to-Sequence Prediction

  2020cites this paper
• Leveraging Geospatial Data Gateways to Support the Operational Application of Deep Learning Models: Vision Paper

  2020cites this paper
• An integrated framework for plant data-driven process modeling using deep-learning with Monte-Carlo simulations

  2020cites this paper
• Computer-aided diagnosis of skin cancer based on soft computing techniques

  2020cites this paper
• Skin cancer diagnosis based on optimized convolutional neural network

  2020cites this paper
• Gated multimodal networks

  2020cites this paper
• Deep learning and optimization algorithms for automatic breast cancer detection

  2020cites this paper
• Tools to reverse-engineer multicellular systems: case studies using the fruit fly

  2019cites this paper
• LNSNet: Lightweight Navigable Space Segmentation for Autonomous Robots on Construction Sites

  2019cites this paper
• Sequence-to-sequence learning for machine translation and automatic differentiation for machine learning software tools

  2019cites this paper
• Overview of currency recognition using deep learning

  2019cites this paper
• A Framework for Preprocessing Multivariate, Topology-Aware Time Series and Event Data in a Multi-System Environment

  2019cites this paper
• Hierarchical Motion Segmentation Through sEMG for Continuous Lower Limb Motions

  2019influential citation
• Open-Source Practices for Music Signal Processing Research: Recommendations for Transparent, Sustainable, and Reproducible Audio Research

  2019cites this paper
• Benchmarking Deep Learning Hardware and Frameworks: Qualitative Metrics.

  2019cites this paper
• Keras Spatial: Extending deep learning frameworks for preprocessing and on-the-fly augmentation of geospatial data

  2019cites this paper
• Predicting Shipping Time with Machine Learning

  2019cites this paper
• Optimization of the Convolutional Neural Networks for Automatic Detection of Skin Cancer

  2019cites this paper
• Learning robotic manipulation from user demonstrations 2017

  2019cites this paper
• Computational Tools for Annotating Antibiotic Resistance in Metagenomic Data

  2019cites this paper
• Image Recognition of Coal and Coal Gangue Using a Convolutional Neural Network and Transfer Learning

  2019cites this paper
• Structured Inference for Recurrent Hidden Semi-markov Model

  2018cites this paper
• Towards Two-Dimensional Sequence to Sequence Model in Neural Machine Translation

  2018cites this paper
• Multimodal representation learning with neural networks

  2018cites this paper
• Auto-Encoding Dictionary Definitions into Consistent Word Embeddings

  2018cites this paper
• The RWTH Aachen University Filtering System for the WMT 2018 Parallel Corpus Filtering Task

  2018cites this paper
• 3D Convolutional Neural Networks for Dynamic Sign Language Recognition

  2018cites this paper
• Generative models for natural images

  2018cites this paper
• An Overview of Machine Learning and HPC in Open Sources for Bioinformatics*

  2018cites this paper
• Applications Research of Machine Learning Algorithm in Translation System

  2018cites this paper
• Feedforward deep architectures for classification and synthesis

  2018cites this paper
• Less is more: why all paradigms are defective, and why that is a good thing

  2018cites this paper
• Currency Recognition Using Deep Learning

  2018cites this paper
• Neural Machine Translation Decoding with Terminology Constraints

  2018cites this paper
• Accelerating NMT Batched Beam Decoding with LMBR Posteriors for Deployment

  2018cites this paper
• Overcoming Catastrophic Forgetting in Convolutional Neural Networks by Selective Network Augmentation

  2018cites this paper
• One deep music representation to rule them all? A comparative analysis of different representation learning strategies

  2018cites this paper
• Why not be Versatile? Applications of the SGNMT Decoder for Machine Translation

  2018cites this paper
• A Survey on Deep Learning Methods for Robot Vision

  2018cites this paper
• Design and implementation of DeepDSL: A DSL for deep learning

  2018cites this paper
• Nested LSTMs

  2018cites this paper
• DeepTC – An Extension of DKPro Text Classification for Fostering Reproducibility of Deep Learning Experiments

  2018cites this paper
• Real-Time Prediction of Taxi Demand Using Recurrent Neural Networks

  2018cites this paper
• Recent Advances in Deep Learning: An Overview

  2018cites this paper
• Learning to Compute Word Embeddings On the Fly

  2017cites this paper
• Combining Data-Driven 2D and 3D Human Appearance Models

  2017cites this paper
• Applying compensation techniques on i-vectors extracted from short-test utterances for speaker verification using deep neural network

  2017cites this paper
• Forecasting Stock Prices from the Limit Order Book Using Convolutional Neural Networks

  2017cites this paper
• Deep Collective Inference

  2017cites this paper
• Gated Multimodal Units for Information Fusion

  2017cites this paper
• Natural Language Generation for Open Domain Human-Robot Interaction

  2017cites this paper
• Recurrent Normalization Propagation

  2017cites this paper
• Sequence Prediction with Unlabeled Data by Reward Function Learning

  2017cites this paper
• Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search

  2017cites this paper
• The RWTH Aachen Machine Translation Systems for IWSLT 2017

  2017cites this paper
• Boundary-Seeking Generative Adversarial Networks

  2017cites this paper
• SGNMT – A Flexible NMT Decoding Platform for Quick Prototyping of New Models and Search Strategies

  2017cites this paper
• Unfolding and Shrinking Neural Machine Translation Ensembles

  2017cites this paper
• Learning robotic manipulation from user demonstrations

  2017cites this paper
• A Sequence Learning Model with Recurrent Neural Networks for Taxi Demand Prediction

  2017cites this paper
• A Deep learning toolkit for high dimensional sequential data

  2017cites this paper
• Automatic Scansion of Poetry

  2017cites this paper
• A robust adaptive stochastic gradient method for deep learning

  2017cites this paper
• Neural Monkey: An Open-source Tool for Sequence Learning

  2017cites this paper
• Stochastic Sequential Neural Networks with Structured Inference

  2017cites this paper
• Multi-level Representations for Fine-Grained Typing of Knowledge Base Entities

  2017cites this paper
• Generating Alignments Using Target Foresight in Attention-Based Neural Machine Translation

  2017cites this paper
• Learning discriminative features from electroencephalography recordings by encoding similarity constraints

  2017cites this paper
• Sequence-to-sequence models for punctuated transcription combining lexical and acoustic features

  2017cites this paper
• Source sentence simplification for statistical machine translation

  2017cites this paper
• Action Classification and Highlighting in Videos

  2017cites this paper
• Empirical Investigation of Optimization Algorithms in Neural Machine Translation

  2017cites this paper
• Deep Character-Level Neural Machine Translation By Learning Morphology

  2017cites this paper
• Language Modelling for Handwriting Recognition

  2017cites this paper
• Char2Wav: End-to-End Speech Synthesis

  2017cites this paper
• Twin Networks: Using the Future as a Regularizer

  2017cites this paper
• On Multilingual Training of Neural Dependency Parsers

  2017cites this paper
• TensorFlow Estimators: Managing Simplicity vs. Flexibility in High-Level Machine Learning Frameworks

  2017cites this paper