{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/dynamic-neural-turing-machine-with-soft-and","title":"Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes","arxiv_id":"1607.00036","date":"2016-06-30","proceeding":null,"authors":["Caglar Gulcehre","Sarath Chandar","Kyunghyun Cho","Yoshua Bengio"],"abstract":"We extend neural Turing machine (NTM) model into a dynamic neural Turing\nmachine (D-NTM) by introducing a trainable memory addressing scheme. This\naddressing scheme maintains for each memory cell two separate vectors, content\nand address vectors. This allows the D-NTM to learn a wide variety of\nlocation-based addressing strategies including both linear and nonlinear ones.\nWe implement the D-NTM with both continuous, differentiable and discrete,\nnon-differentiable read/write mechanisms. We investigate the mechanisms and\neffects of learning to read and write into a memory through experiments on\nFacebook bAbI tasks using both a feedforward and GRUcontroller. The D-NTM is\nevaluated on a set of Facebook bAbI tasks and shown to outperform NTM and LSTM\nbaselines. We have done extensive analysis of our model and different\nvariations of NTM on bAbI task. We also provide further experimental results on\nsequential pMNIST, Stanford Natural Language Inference, associative recall and\ncopy tasks.","url_abs":"http://arxiv.org/abs/1607.00036v2","url_pdf":"http://arxiv.org/pdf/1607.00036v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[{"method_slug":"content-based-attention","method_name":"Content-based Attention"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"location-based-attention","method_name":"Location-based Attention"},{"method_slug":"neural-turing-machine","method_name":"Neural Turing Machine"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-babi","task":"Question Answering","dataset":"bAbi","model":"DMN+","rank_in_archive_order":5,"of":14,"metrics":{"Accuracy (trained on 10k)":"97.2%","Accuracy (trained on 1k)":"66.8%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1607.00036","atlas_url":"https://app.syntology.ai/?focus=1607.00036","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1607.00036"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1607.00036\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1607.00036"},"call":"get_concepts_for_paper(arxiv_id=\"1607.00036\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"f5313f6d0ce17dfffe9d7d338c056b03edc279818d652ae0b6f7558a09deca8a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}