- Full text PDF available (10)
- This year (6)
- Last 5 years (11)
- Last 10 years (11)
Journals and Conferences
We propose a novel biologically plausible actor-critic algorithm using policy gradients in order to achieve practical, model-free reinforcement learning. It does not rely on backpropagation and is the first neural actor-critic relying only on locally available information. We show it has an advantage over pure policy gradients methods for motor learning… (More)
Computer simulations have become a very powerful tool for scientific research. In order to facilitate research in computational biology, the BioDynaMo project aims at a general platform for biological computer simulations, which should be executable on hybrid cloud computing systems. This paper describes challenges and lessons learnt during the early stages… (More)
Catastrophic forgetting is of special importance in reinforcement learning, as the data distribution is generally non-stationary over time. We study and compare several pseudorehearsal approaches for Qlearning with function approximation in a pole balancing task. We have found that pseudorehearsal seems to assist learning even in such very simple problems,… (More)
Computer simulations have become a very powerful tool for scientific research. Given the vast complexity that comes with many open scientific questions, a purely analytical or experimental approach is often not viable. For example, biological systems (such as the human brain) comprise an extremely complex organization and heterogeneous interactions across… (More)
This paper is a brief update on developments in the BioDynaMo project, a new platform for computer simulations for biological research. We will discuss the new capabilities of the simulator, important new concepts simulation methodology as well as its numerous applications to the computational biology and nanoscience communities.
Spatial organization is a core challenge for all large agent-based models with local interactions. In biological tissue models, spatial search and reinsertion are frequently reported as the most expensive steps of the simulation. One of the main methods utilized in order to maintain both favourable algorithmic complexity and accuracy is spatial hierarchies.… (More)
Music holds a significant cultural role in social identity and in the encouragement of socialization. Technology, by the destruction of physical and cultural distance, has lead to many changes in musical themes and the complete loss of forms. Yet, it also allows for the preservation and distribution of music from societies without a history of written sheet… (More)
Formal modelling languages play a key role in the development of soware since they enable users to prove correctness of system properties. However, there is still not a clear understanding on how to map a formal model to a specic programming language. In order to propose a solution, this paper presents a source-to-source mapping between EventB models and… (More)
In this paper we propose an algorithm, Simple Hebbian PCA, and prove that it is able to calculate the principal component analysis (PCA) in a distributed fashion across nodes. It simplifies existing network structures by removing intralayer weights, essentially cutting the number of weights that need to be trained in half.