litlas
ログインアカウント作成

Neural Turing Machines

著者: Alex Graves, Greg Wayne, Ivo Danihelka - arXiv 2014 被引用: 1,216

We extend the capabilities of neural networks by coupling them to external memory resources, which they can interact with by attentional processes. The combined system is analogous to a Turing Machine or Von Neumann architecture but is differentiable end-to-end, allowing it to be efficiently trained with gradient descent. Preliminary results demonstrate that Neural Turing Machines can infer simple algorithms such as copying, sorting, and associative recall from input and output examples.

The magical numberseven, plus or minus…The magical number seven, plus or minus two: Some limits on our capacity for processing information.Neural networks andphysical systems with…Neural networks and physical systems with emergent collective computational abilities.On the ComputationalPower of Neural NetsOn the Computational Power of Neural NetsLong Short-Term MemoryLong Short-Term MemoryLearning to Learn UsingGradient DescentLearning to Learn Using Gradient DescentSimple substrates forcomplex cognitionSimple substrates for complex cognitionLOL: An Investigationinto Cybernetic Humor…LOL: An Investigation into Cybernetic Humor, or: Can Machines Laugh?Generating SequencesWith Recurrent Neural…Generating Sequences With Recurrent Neural NetworksSpeech Recognition withDeep Recurrent Neural…Speech Recognition with Deep Recurrent Neural NetworksSequence to SequenceLearning with Neural…Sequence to Sequence Learning with Neural NetworksTowards End-To-EndSpeech Recognition with…Towards End-To-End Speech Recognition with Recurrent Neural NetworksNeural MachineTranslation by Jointly…Neural Machine Translation by Jointly Learning to Align and TranslateAsk, Attend and Answer:Exploring…Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question AnsweringLearning SimpleAlgorithms from ExamplesLearning Simple Algorithms from ExamplesAn OnlineSequence-to-Sequence…An Online Sequence-to-Sequence Model Using Partial ConditioningProgressive AttentionNetworks for Visual…Progressive Attention Networks for Visual Attribute PredictionSequentialRecommendation with Use…Sequential Recommendation with User Memory NetworksAttention-based GraphNeural Network for…Attention-based Graph Neural Network for Semi-supervised LearningFitting New SpeakersBased on a Short…Fitting New Speakers Based on a Short Untranscribed SampleCAWET: Context-AwareWorst-Case Execution…CAWET: Context-Aware Worst-Case Execution Time Estimation Using TransformersNeural Logic MachinesNeural Logic MachinesAn Introductory Surveyon Attention Mechanisms…An Introductory Survey on Attention Mechanisms in NLP ProblemsMAST: A Memory-AugmentedSelf-Supervised TrackerMAST: A Memory-Augmented Self-Supervised TrackerLeave No Context Behind:Efficient Infinite…Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attentionNeural Turing MachinesNeural Turing Machines過去の参考文献中心の論文この論文を引用する論文古い新しい

ノードをクリックするとフォーカスを固定、空白をクリックすると本論文に戻ります。ホバーで一時的にプレビューできます。各ノードのページはタイトルから開けます。