35 citations · 43 across the 11 of their papers we have counts for
12 papers
Task-guided cross-subject latent alignment: a multi-encoder-decoder VAE
Angeliki Papathanasiou, Jascha Achterberg, Thomas E. Nichols +1
Aligning neural activity across subjects offers the promise of discovering shared computational principles and generalizable decoders. However, traditional alignment methods requir…
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…
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…
Exploiting heterogeneous delays for efficient computation in low-bit neural networks
Pengfei Sun, Jascha Achterberg, Zhe Su +2
Neural networks rely on learning synaptic weights. However, this overlooks other neural parameters that can also be learned and may be utilized by the brain. One such parameter is…
Brain-Like Processing Pathways Form in Models With Heterogeneous Experts
Jack Cook, Danyal Akarca, Rui Ponte Costa +1
The brain is made up of a vast set of heterogeneous regions that dynamically organize into pathways as a function of task demands. Examples of such pathways can be found in the int…
Accelerated AI Inference via Dynamic Execution Methods
Haim Barad, Jascha Achterberg, Tien Pei Chou +1
In this paper, we focus on Dynamic Execution techniques that optimize the computation flow based on input. This aims to identify simpler problems that can be solved using fewer res…
Dynamical similarity analysis can identify compositional dynamics developing in RNNs
Quentin Guilhot, Michał Wójcik, Jascha Achterberg +1
Methods for analyzing representations in neural systems have become a popular tool in both neuroscience and mechanistic interpretability. Having measures to compare how similar act…
Spatial embedding promotes a specific form of modularity with low entropy and heterogeneous spectral dynamics
Cornelia Sheeran, Andrew S. Ham, Duncan E. Astle +2
Understanding how biological constraints shape neural computation is a central goal of computational neuroscience. Spatially embedded recurrent neural networks provide a promising…
Multilevel Interpretability Of Artificial Neural Networks: Leveraging Framework And Methods From Neuroscience
Zhonghao He, Jascha Achterberg, Katie Collins +13
As deep learning systems are scaled up to many billions of parameters, relating their internal structure to external behaviors becomes very challenging. Although daunting, this pro…
Getting aligned on representational alignment
Ilia Sucholutsky, Lukas Muttenthaler, Adrian Weller +30
Biological and artificial information processing systems form representations of the world that they can use to categorize, reason, plan, navigate, and make decisions. How can we m…
Brain-inspired learning in artificial neural networks: a review
Samuel Schmidgall, Jascha Achterberg, Thomas Miconi +4
Artificial neural networks (ANNs) have emerged as an essential tool in machine learning, achieving remarkable success across diverse domains, including image and speech generation,…
Building artificial neural circuits for domain-general cognition: a primer on brain-inspired systems-level architecture
Jascha Achterberg, Danyal Akarca, Moataz Assem +3
There is a concerted effort to build domain-general artificial intelligence in the form of universal neural network models with sufficient computational flexibility to solve a wide…