{"url":"/method/dynamic-memory-network","slug":"dynamic-memory-network","name":"Dynamic Memory Network","full_name":"Dynamic Memory Network","full_name_withheld":false,"description_markdown":"A **Dynamic Memory Network** is a neural network architecture which processes input sequences and questions, forms episodic memories, and generates relevant answers. Questions trigger an iterative attention process which allows the model to condition its attention on the inputs and the result of previous iterations. These results are then reasoned over in a hierarchical recurrent sequence model to generate answers. \r\n\r\nThe DMN consists of a number of modules:\r\n\r\n- Input Module: The input module encodes raw text inputs from the task into distributed vector representations. The input takes forms like a sentence, a long story, a movie review and so on.\r\n- Question Module: The question module encodes the question of the task into a distributed\r\nvector representation. For question answering, the question may be a sentence such as \"Where did the author first fly?\". The representation is fed into the episodic memory module, and forms the basis, or initial state, upon which the episodic memory module iterates.\r\n- Episodic Memory Module: Given a collection of input representations, the episodic memory module chooses which parts of the inputs to focus on through the attention mechanism. It then produces a ”memory” vector representation taking into account the question as well as the previous memory. Each iteration provides the module with newly relevant information about the input. In other words,\r\nthe module has the ability to retrieve new information, in the form of input representations, which were thought to be irrelevant in previous iterations.\r\n- Answer Module: The answer module generates an answer from the final memory vector of the memory module.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Ask Me Anything: Dynamic Memory Networks for Natural Language Processing","paper":"/paper/ask-me-anything-dynamic-memory-networks-for","first_author":"Ankit Kumar","n_authors":9,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/ask-me-anything-dynamic-memory-networks-for"},"source":{"url":"http://arxiv.org/abs/1506.07285v5","title":"Ask Me Anything: Dynamic Memory Networks for Natural Language Processing","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/rgsachin/DMTN","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Working Memory Models","url":"/methods/category/working-memory-models","pwc_aliases":[]}],"n_papers_tagged":19,"archive_num_papers":19,"papers_newest_first":[{"paper":"/paper/pattern-matching-dynamic-memory-network-for-1","title":"Pattern-Matching Dynamic Memory Network for Dual-Mode Traffic Prediction","date":"2024-08-12","arxiv_id":"2408.07100","n_code_links":1,"syntology":null},{"paper":"/paper/lvos-a-benchmark-for-long-term-video-object","title":"LVOS: A Benchmark for Long-term Video Object Segmentation","date":"2022-11-18","arxiv_id":"2211.10181","n_code_links":1,"syntology":null},{"paper":"/paper/learning-quality-aware-dynamic-memory-for","title":"Learning Quality-aware Dynamic Memory for Video Object Segmentation","date":"2022-07-16","arxiv_id":"2207.07922","n_code_links":1,"syntology":{"ran":0,"of":1,"unverified":1,"pointer_only":1}},{"paper":"/paper/memory-based-semantic-parsing","title":"Memory-Based Semantic Parsing","date":"2021-09-07","arxiv_id":"2110.07358","n_code_links":1,"syntology":null},{"paper":null,"title":"Video Object Segmentation With Dynamic Memory Networks and Adaptive Object Alignment","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/dual-dynamic-memory-network-for-end-to-end","title":"Dual Dynamic Memory Network for End-to-End Multi-turn Task-oriented Dialog Systems","date":"2020-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/dynamic-memory-enhanced-transformer-for-end","title":"Contextualize Knowledge Bases with Transformer for End-to-end Task-Oriented Dialogue Systems","date":"2020-10-12","arxiv_id":"2010.05740","n_code_links":0,"syntology":null},{"paper":null,"title":"Doctor2Vec: Dynamic Doctor Representation Learning for Clinical Trial Recruitment","date":"2019-11-23","arxiv_id":"1911.10395","n_code_links":0,"syntology":null},{"paper":"/paper/meta-learning-with-dynamic-memory-based","title":"Meta-Learning with Dynamic-Memory-Based Prototypical Network for Few-Shot Event Detection","date":"2019-10-25","arxiv_id":"1910.11621","n_code_links":1,"syntology":null},{"paper":null,"title":"Entropy-Enhanced Multimodal Attention Model for Scene-Aware Dialogue Generation","date":"2019-08-22","arxiv_id":"1908.08191","n_code_links":0,"syntology":null},{"paper":null,"title":"Visual Tracking via Dynamic Memory Networks","date":"2019-07-12","arxiv_id":"1907.07613","n_code_links":0,"syntology":null},{"paper":"/paper/exploiting-contextual-information-via-dynamic","title":"Exploiting Contextual Information via Dynamic Memory Network for Event Detection","date":"2018-10-03","arxiv_id":"1810.03449","n_code_links":1,"syntology":null},{"paper":null,"title":"Relational dynamic memory networks","date":"2018-08-10","arxiv_id":"1808.04247","n_code_links":0,"syntology":null},{"paper":"/paper/motion-appearance-co-memory-networks-for","title":"Motion-Appearance Co-Memory Networks for Video Question Answering","date":"2018-03-29","arxiv_id":"1803.10906","n_code_links":0,"syntology":null},{"paper":"/paper/learning-dynamic-memory-networks-for-object","title":"Learning Dynamic Memory Networks for Object Tracking","date":"2018-03-20","arxiv_id":"1803.07268","n_code_links":1,"syntology":{"ran":0,"of":7,"unverified":7,"pointer_only":0}},{"paper":null,"title":"Integrating Order Information and Event Relation for Script Event Prediction","date":"2017-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/ask-me-even-more-dynamic-memory-tensor","title":"Ask Me Even More: Dynamic Memory Tensor Networks (Extended Model)","date":"2017-03-11","arxiv_id":"1703.03939","n_code_links":2,"syntology":null},{"paper":"/paper/dynamic-memory-networks-for-visual-and","title":"Dynamic Memory Networks for Visual and Textual Question Answering","date":"2016-03-04","arxiv_id":"1603.01417","n_code_links":10,"syntology":{"ran":7,"of":7,"unverified":0,"pointer_only":7}},{"paper":"/paper/ask-me-anything-dynamic-memory-networks-for","title":"Ask Me Anything: Dynamic Memory Networks for Natural Language Processing","date":"2015-06-24","arxiv_id":"1506.07285","n_code_links":10,"syntology":{"ran":2,"of":5,"unverified":3,"pointer_only":0}}],"papers_shown":19,"tasks":[{"task":"/task/question-answering","name":"Question Answering","papers":4},{"task":"/task/object","name":"Object","papers":3},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":3},{"task":"/task/video-object-segmentation","name":"Video Object Segmentation","papers":3},{"task":"/task/video-semantic-segmentation","name":"Video Semantic Segmentation","papers":3},{"task":"/task/event-detection","name":"Event Detection","papers":2},{"task":"/task/semi-supervised-video-object-segmentation","name":"Semi-Supervised Video Object Segmentation","papers":2},{"task":"/task/template-matching","name":"Template Matching","papers":2},{"task":"/task/visual-question-answering","name":"Visual Question Answering (VQA)","papers":2},{"task":"/task/visual-tracking","name":"Visual Tracking","papers":2},{"task":"/task/clinical-knowledge","name":"Clinical Knowledge","papers":1},{"task":"/task/decoder","name":"Decoder","papers":1},{"task":"/task/dialogue-generation","name":"Dialogue Generation","papers":1},{"task":"/task/event-extraction","name":"Event Extraction","papers":1},{"task":"/task/few-shot-learning","name":"Few-Shot Learning","papers":1},{"task":"/task/classification","name":"General Classification","papers":1},{"task":"/task/language-modeling","name":"Language Modeling","papers":1},{"task":"/task/language-modelling","name":"Language Modelling","papers":1},{"task":"/task/meta-learning","name":"Meta-Learning","papers":1},{"task":"/task/object-tracking","name":"Object Tracking","papers":1}],"tasks_shown":20,"n_tasks":36,"usage_by_year":[{"year":"2015","papers":1},{"year":"2016","papers":1},{"year":"2017","papers":2},{"year":"2018","papers":4},{"year":"2019","papers":4},{"year":"2020","papers":2},{"year":"2021","papers":2},{"year":"2022","papers":2},{"year":"2024","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/dynamic-memory-network"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}