Towards Simulating the Human Brain

Abstract

Understanding the human brain is still one of the biggest scientific challenges. The European Human Brain Project tries to tackle this challenge, by integrating a wide range of neuroscientific data into large multi-scale models and simulations of the brain. In this talk, I will highlight recent results and challenges that we face in our endeavour to reconstruct and simulate models of entire brains. The human brain is comprised of 80 billion neurons and 100*1012 synapses, each with dynamic properties that are governed by many differential equations. Representing the dynamic state of a complete human brain thus is still outside the reach of even the largest super-computers. Models of a mouse brain, still comprise 75 million neurons and 80 billion connections, but these are accessible with model supercomputers. In the first part of the talk, I will outline how high-resolution imaging data can be used to semi-automatically reconstruct 3D the positions of different neuron types as well as their connections. Next, I will discuss the challenges of representing and simulating such large-scale models using hybrid time and event driven simulation techniques. Finally, I will discuss applications of large-scale brain models for neuroscience, medicine, robotics and computing technology.