Will
9 followers · 6 following · 1490 views
on the atlas — 55
- Unique games conjecture1 savers
- Artifacts – A Human-Centered Framework for Growing Ideas3 savers
- Ink & Switch30 savers
- Investigations ← Forensic Architecture10 savers
- Teach Yourself Computer Science25 savers
- Internal Combustion Engine4 savers
- Introducing Mercury OS - A speculative vision of the OS8 savers
- Great Founder Theory - Samo Burja14 savers
- Ian Gemp6 savers
- Hopfield network7 savers
- What every computer science major should know11 savers
- Curius / Bookmarks for the extremely curious182 savers
- WTF Happened In 1971?11 savers
- Category Theory Illustrated - Orders4 savers
- Schumacher College - Higher Education at Dartington Trust1 savers
- Richard D. Alexander1 savers
- fastText3 savers
- 10 Papers Every Developer Should Read2 savers
- Dynamics of Symmetry Group Theorizing2 savers
- Knot Theory1 savers
- Rosetta Code1 savers
- Programming Languages - Hyperpolyglot2 savers
- Introduction to Locality-Sensitive Hashing1 savers
- Tf-idf :: A Single-Page Tutorial - Information Retrieval and Text Mining1 savers
- Consensus Multiplicative Weights Update: Learningto Learn using Projector-based Game Signatures1 savers
- nkandswitch/ksp: Reference implementation of Knowledge Server Protocol (KSP)1 savers
- Supercharging UK Science and Innovation1 savers
- Martin Powell1 savers
- Overview - Troika JS1 savers
- Cryptovoxels1 savers
- CRDT Optimizations1 savers
- 3 Kinds of Tech Debt | Byte Size Theories1 savers
- A Lecture on Partial Differential Equations1 savers
- Robert Trivers1 savers
- media.bitcoinfiles.org/25fd3c432d3298893c000e9851bc093c41bd4d5324d72ac5ddf9df2adb4ea5c71 savers
- Speeding Up the Webcola Graph Viz Library with Rust + WebAssembly - Casey Primozic's Homepage2 savers
- Natural Intelligence2 savers
- Researchers investigate the spread of weighing systems across Western Eurasia 4,000 years ago - The Archaeology News Network1 savers
- The agencies method for coalition formation inexperimental games - John Nash1 savers
- Parallel Control1 savers
- Qvault computer science curriculum1 savers
- Game theory as an engine for large-scale data analysis | DeepMind2 savers
- Computers and Creativity13 savers
- [1911.01547] On the Measure of Intelligence12 savers
- Web Browser Engineering11 savers
- Obsidian9 savers
- Understanding UMAP9 savers
- Red Blob Games8 savers
- Computing History Hub8 savers
- The Building Blocks of Interpretability6 savers
- Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges5 savers
- We were promised Strong AI, but instead we got metadata analysis3 savers
- Git from the Bottom Up3 savers
- Twelve Month Woodworking Course – Rowden Atelier2 savers
- Arkipelago.space2 savers
highlights — 3
Hopfield networks serve as content-addressable ("associative") memory systems with binary threshold nodes, or with continuous variables.[6] Hopfield networks also provide a model for understanding human memory.[7][8]
Hopfield networkThe Ising model of a recurrent neural network as a learning memory model was first proposed by Shun'ichi Amari in 1972[2][3] and then by William A. Little in 1974,[4] who was acknowledged by Hopfield in his 1982 paper.[1] Networks with continuous dynamics were developed by Hopfield in his 1984 paper.[6] A major advance in memory storage capacity was developed by Krotov and Hopfield in 2016[9] through a change in network dynamics and energy function. This idea was further extended by Demircigil and collaborators in 2017.[10] The continuous dynamics of large memory capacity models was developed …
Hopfield networkOne version of this question—reminiscent of adversarial examples in neural networks—is just to ask what changes need to be made to an initial condition to “flip its result”. Or, put another way: let’s say one has a system (like the GKL rule) that basically achieves correct consensus for almost all randomly chosen initial conditions. Now we ask the question of whether there is a systematic way to tweak a given randomly chosen initial condition to make it “lead to the wrong answer”. (One can think of this as a bit like asking whether one can find a nonce that will make a cryptographic hash come …
The Problem of Distributed Consensus—Stephen Wolfram Writings