Global neural dynamics emerge from multi-scale brain structures, with nodes dynamically communicating to form transient ensembles that may represent neural information. Neural activity can be measured empirically at scales spanning proteins and subcellular domains to neuronal assemblies or whole-brain networks connected through tracts, but it has remained challenging to bridge knowledge between empirically tractable scales. Multi-scale models of brain function have begun to directly link the emergence of global brain dynamics in conscious and unconscious brain states with microscopic changes at the level of cells. In particular, adaptive exponential integrate-and-fire (AdEx) mean-field models representing statistical properties of local populations of neurons have been connected following human tractography data to represent multi-scale neural phenomena in simulations using The Virtual Brain (TVB). While mean-field models can be run on personal computers for short simulations, or in parallel on high-performance computing (HPC) architectures for longer simulations and parameter scans, the computational burden remains red heavy and vast areas of the parameter space remain unexplored. In this work, we report that our HPC framework, a modular set of methods used here to implement the TVB-AdEx model for the graphics processing unit (GPU) and analyze emergent dynamics, notably accelerates simulations and substantially reduces computational resource requirements. The framework preserves the stability and robustness of the TVB-AdEx model, thus facilitating a finer-resolution exploration of vast parameter spaces as well as longer simulations that were previously near impossible to perform. Comparing our GPU implementations of the TVB-AdEx framework with previous implementations using central processing units (CPUs), we first show correspondence of the resulting simulated time-series data from GPU and CPU instantiations. Next, the similarity of parameter combinations, giving rise to patterns of functional connectivity, between brain regions is demonstrated. By varying global coupling together with spike-frequency adaptation, we next replicate previous results indicating inter-dependence of these parameters in inducing transitions between dynamics associated with conscious and unconscious brain states. Upon further exploring parameter space, we report a nonlinear interplay between the spike-frequency adaptation and subthreshold adaptation, as well as previously unappreciated interactions between the global coupling, adaptation, and propagation velocity of action potentials along the human connectome. Given that simulation and analysis toolkits are made public as open-source packages, this framework serves as a template onto which other models can be easily scripted. Further, personalized data-sets can be used for for the creation of red virtual brain twins toward facilitating more precise approaches to the study of epilepsy, sleep, anesthesia, and disorders of consciousness. These results thus represent potentially impactful, publicly available methods for simulating and analyzing human brain states.

Neuroscience education is challenged by rapidly evolving technology and the development of interdisciplinary approaches for brain research. The Human Brain Project (HBP) Education Programme aimed to address the need for interdisciplinary expertise in brain research by equipping a new generation of researchers with skills across neuroscience, medicine, and information technology. Over its ten year duration, the programme engaged over 1,300 experts and attracted more than 5,500 participants from various scientific disciplines in its blended learning curriculum, specialised schools and workshops, and events fostering dialogue among early-career researchers. Key principles of the programme’s approach included fostering interdisciplinarity, adaptability to the evolving research landscape and infrastructure, and a collaborative environment with a focus on empowering early-career researchers. Following the programme’s conclusion, we provide here an analysis and in-depth view across a diverse range of educational formats and events. Our results show that the Education Programme achieved success in its wide geographic reach, the diversity of participants, and the establishment of transversal collaborations. Building on these experiences and achievements, we describe how leveraging digital tools and platforms provides accessible and highly specialised training, which can enhance existing education programmes for the next generation of brain researchers working in decentralised European collaborative spaces. Finally, we present the lessons learnt so that similar initiatives may improve upon our experience and incorporate our suggestions into their own programme.

Neuroscience models commonly have a high number of degrees of freedom and only specific regions within the parameter space are able to produce dynamics of interest. This makes the development of tools and strategies to efficiently find these regions of high importance to advance brain research. Exploring the high dimensional parameter space using numerical simulations has been a frequently used technique in the last years in many areas of computational neuroscience. Today, high performance computing (HPC) can provide a powerful infrastructure to speed up explorations and increase our general understanding of the behavior of the model in reasonable times. Learning to learn (L2L) is a well-known concept in machine learning (ML) and a specific method for acquiring constraints to improve learning performance. This concept can be decomposed into a two loop optimization process where the target of optimization can consist of any program such as an artificial neural network, a spiking network, a single cell model, or a whole brain simulation. In this work, we present L2L as an easy to use and flexible framework to perform parameter and hyper-parameter space exploration of neuroscience models on HPC infrastructure. Learning to learn is an implementation of the L2L concept written in Python. This open-source software allows several instances of an optimization target to be executed with different parameters in an embarrassingly parallel fashion on HPC. L2L provides a set of built-in optimizer algorithms, which make adaptive and efficient exploration of parameter spaces possible. Different from other optimization toolboxes, L2L provides maximum flexibility for the way the optimization target can be executed. In this paper, we show a variety of examples of neuroscience models being optimized within the L2L framework to execute different types of tasks. The tasks used to illustrate the concept go from reproducing empirical data to learning how to solve a problem in a dynamic environment. We particularly focus on simulations with models ranging from the single cell to the whole brain and using a variety of simulation engines like NEST, Arbor, TVB, OpenAIGym, and NetLogo.

Whole brain network models are now an established tool in scientific and clinical research, however their use in a larger workflow still adds significant informatics complexity. We propose a tool, RateML, that enables users to generate such models from a succinct declarative description, in which the mathematics of the model are described without specifying how their simulation should be implemented. RateML builds on NeuroML’s Low Entropy Model Specification (LEMS), an XML based language for specifying models of dynamical systems, allowing descriptions of neural mass and discretized neural field models, as implemented by the Virtual Brain (TVB) simulator: the end user describes their model’s mathematics once and generates and runs code for different languages, targeting both CPUs for fast single simulations and GPUs for parallel ensemble simulations. High performance parallel simulations are crucial for tuning many parameters of a model to empirical data such as functional magnetic resonance imaging (fMRI), with reasonable execution times on small or modest hardware resources. Specifically, while RateML can generate Python model code, it enables generation of Compute Unified Device Architecture C++ code for NVIDIA GPUs. When a CUDA implementation of a model is generated, a tailored model driver class is produced, enabling the user to tweak the driver by hand and perform the parameter sweep. The model and driver can be executed on any compute capable NVIDIA GPU with a high degree of parallelization, either locally or in a compute cluster environment. The results reported in this manuscript show that with the CUDA code generated by RateML, it is possible to explore thousands of parameter combinations with a single Graphics Processing Unit for different models, substantially reducing parameter exploration times and resource usage for the brain network models, in turn accelerating the research workflow itself. This provides a new tool to create efficient and broader parameter fitting workflows, support studies on larger cohorts, and derive more robust and statistically relevant conclusions about brain dynamics.

The Virtual Brain (TVB) is now available as open-source services on the cloud research platform EBRAINS (ebrains.eu). It offers software for constructing, simulating and analysing brain network models including the TVB simulator; magnetic resonance imaging (MRI) processing pipelines to extract structural and functional brain networks; combined simulation of large-scale brain networks with small-scale spiking networks; automatic conversion of user-specified model equations into fast simulation code; simulation-ready brain models of patients and healthy volunteers; Bayesian parameter optimization in epilepsy patient models; data and software for mouse brain simulation; and extensive educational material. TVB cloud services facilitate reproducible online collaboration and discovery of data assets, models, and software embedded in scalable and secure workflows, a precondition for research on large cohort data sets, better generalizability, and clinical translation.

In-silico brain simulations are the de-facto tools computational neuroscientists use to understand large-scale and complex brain-function dynamics. Current brain simulators do not scale efficiently enough to large-scale problem sizes (e.g., >100,000 neurons) when simulating biophysically complex neuron models. The goal of this work is to explore the use of true multi-GPU acceleration through NVIDIA’s GPUDirect technology on computationally challenging brain models and to assess their scalability. The brain model used is a state-of-the-art, extended Hodgkin-Huxley, biophysically meaningful, three-compartmental model of the inferior-olivary nucleus. The Hodgkin-Huxley model is the most widely adopted conductance-based neuron representation, and thus the results from simulating this representative workload are relevant for many other brain experiments. Not only the actual network-simulation times but also the network-setup times were taken into account when designing and benchmarking the multi-GPU version, an aspect often ignored in similar previous work. Network sizes varying from 65K to 2M cells, with 10 and 1,000 synapses per neuron were executed on 8, 16, 24, and 32 GPUs. Without loss of generality, simulations were run for 100 ms of biological time. Findings indicate that communication overheads do not dominate overall execution while scaling the network size up is computationally tractable. This scalable design proves that large-network simulations of complex neural models are possible using a multi-GPU design with GPUDirect.