8 papers
Unifying Dynamical Systems and Graph Theory to Mechanistically Understand Computation in Neural Networks
Jatin Sharma, Dan F. M Goodman, Danyal Akarca
Understanding how biological and artificial neural networks implement computation from connectivity is a central problem in neuroscience and machine learning. In neural systems, st…
Algorithm-hardware co-design of neuromorphic networks with dual memory pathways
Pengfei Sun, Zhe Su, Jascha Achterberg +3
Spiking neural networks excel at event-driven sensing. Yet, maintaining task-relevant context over long timescales both algorithmically and in hardware, while respecting both tight…
The Principle of Maximum Heterogeneity Optimises Productivity in Distributed Production Systems Across Biology, Economics, and Computing
Guillhem Artis, Danyal Akarca, Jascha Achterberg
The world is full of systems of distributed agents, collaborating and competing in complex ways: firms and workers specialise within economies, neurons adapt their tuning across br…
Belief Propagation Converges to Gaussian Distributions in Sparsely-Connected Factor Graphs
Tom Yates, Yuzhou Cheng, Ignacio Alzugaray +3
Belief Propagation (BP) is a powerful algorithm for distributed inference in probabilistic graphical models, however it quickly becomes infeasible for practical compute and memory…
Space as Time Through Neuron Position Learning
Balázs Mészáros, James C. Knight, Danyal Akarca +1
Biological neural networks exist in physical space where distance influences communication delays: a fundamental coupling between space and time absent in most artificial neural ne…
Self-motion as a structural prior for coherent and robust formation of cognitive maps
Yingchao Yu, Pengfei Sun, Yaochu Jin +7
Most computational accounts of cognitive maps assume that stability is achieved primarily through sensory anchoring, with self-motion contributing to incremental positional updates…