--- title: "Dylan Banarse — author profile and papers — Elamur Research" description: "Dylan Banarse: 2 papers on Elamur Research (2017–2023), h-index 8 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/dylan-banarse/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/dylan-banarse/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Dylan Banarse # Dylan Banarse Dylan Banarse has 2 papers in our library, in 2017–2023; often with [Chrisantha Fernando](https://md.research.elamur.ai/free/en/authors/chrisantha-fernando/), [Alexander Pritzel](https://md.research.elamur.ai/free/en/authors/alexander-pritzel/), [Charles Blundell](https://md.research.elamur.ai/free/en/authors/charles-blundell/). 2 papers in our library · 2017–2023 [OpenAlex](https://openalex.org/A5011829015) · [**h-index 8**](https://openalex.org/authors/A5011829015) · [20 works](https://openalex.org/works?filter=author.id:A5011829015) · [1,630 citations](https://openalex.org/works?filter=author.id:A5011829015&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 2 works in our library](https://md.research.elamur.ai/free/en/authors/dylan-banarse/#papers) · [🔗 Cited 2,533 times in our library](https://md.research.elamur.ai/free/en/authors/dylan-banarse/cited-by/) · [1 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #3048](https://md.research.elamur.ai/free/en/paper-stars/page/31/#star-3048) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Dylan+Banarse) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Dylan+Banarse) · [dblp](https://dblp.org/search?q=Dylan+Banarse) · [ACL Anthology](https://aclanthology.org/search/?q=Dylan+Banarse) ## Affiliations [🏢**Google DeepMind** London · United Kingdom 2016–2024 · 4 papers](https://md.research.elamur.ai/free/en/companies/google-deepmind/) · [🎓**Bangor University** Bangor · United Kingdom 1997–2002 · 4 papers](https://ror.org/006jb1a24) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. ## Fields, topics and concepts Of its works in our library, with the number of works on each. 📚 Shelves 4 The field of science this work belongs to (OpenAlex fields).[Artificial Intelligence · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Computer Science · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Arts and Humanities · 1 work](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Language and Linguistics · 1 work](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) ## Works by year ### 2020s [**2023** 1 paper](https://md.research.elamur.ai/free/en/authors/dylan-banarse/year/2023/) ### 2010s [**2017** 1 paper](https://md.research.elamur.ai/free/en/authors/dylan-banarse/year/2017/) ## Papers The most cited first (OpenAlex and our library). 1. **[PathNet: Evolution Channels Gradient Descent in Super Neural Networks](https://md.research.elamur.ai/free/en/papers/fernando-2017-pathnet-evolution-channels-gradient-descent/)** *(2017 · 667 citations)* The paper asks how one very large neural network could learn many tasks one after another. The goal is to reuse earlier knowledge without overwriting it, which is known as catastrophic forgetting. The authors propose PathNet, a modular network of several layers, each with many small modules. A population of… 2. **[Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://md.research.elamur.ai/free/en/papers/fernando-2023-promptbreeder-self-referential-self-improvement/)** *(2023 · 174 citations)* Hand-written prompting strategies like Chain-of-Thought help LLMs reason, but they are generic and seldom the best choice for a particular task. ## All works 3 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them. 1. [**PathNet: Evolution Channels Gradient Descent in Super Neural Networks arXiv:1701.08734**Chrisantha Fernando, Dylan Banarse, Charles Blundell, et al.*2017 · 667 citations*](https://md.research.elamur.ai/free/en/papers/fernando-2017-pathnet-evolution-channels-gradient-descent/) 2. [**Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution arXiv:2309.16797**Chrisantha Fernando, Dylan Banarse, Henryk Michalewski, et al.*2023 · 174 citations*](https://md.research.elamur.ai/free/en/papers/fernando-2023-promptbreeder-self-referential-self-improvement/) 3. **[Perception Test: A Diagnostic Benchmark for Multimodal Video Models ↗](https://doi.org/10.52202/075280-1852) neural information processing systems · no summary yet**Viorica Pătrăucean et al.*2023 · 113 citations* ## Co-authors here 7 co-authors with a page, the most papers together first. - [Chrisantha Fernando](https://md.research.elamur.ai/free/en/authors/chrisantha-fernando/) ×2 - [Alexander Pritzel](https://md.research.elamur.ai/free/en/authors/alexander-pritzel/) - [Charles Blundell](https://md.research.elamur.ai/free/en/authors/charles-blundell/) - [Daan Wierstra](https://md.research.elamur.ai/free/en/authors/daan-wierstra/) - [David Ha](https://md.research.elamur.ai/free/en/authors/david-ha/) - [Henryk Michalewski](https://md.research.elamur.ai/free/en/authors/henryk-michalewski/) - [Tim Rocktaschel](https://md.research.elamur.ai/free/en/authors/tim-rocktaschel/) ## Venues Where their works here were published, the most works first, with the editions of those that have a page. - neural information processing systems ## Cited by Papers of our library cite their works 2,533 times (of the 149,439 papers whose bibliographies we read); [615 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/dylan-banarse/cited-by/). Updated 2 November 2026