Related Experiment Video
Updated: Jul 19, 2026
11:18
Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
Published on: March 2, 2015
10.8K
BRAID: Input-driven nonlinear dynamical modeling of neural-behavioral data.
Parsa Vahidi1, Omid G Sani1, Maryam M Shanechi1,2,3
1Electrical and Computer Engineering, University of Southern California (USC), Los Angeles, CA.
Arxiv
|October 3, 2025
Summary
We developed BRAID, a deep learning framework that models neural dynamics by incorporating external inputs. This method accurately captures neural-behavioral relationships and improves forecasting by disentangling intrinsic dynamics from input effects.
Area of Science:
- Computational Neuroscience
- Machine Learning
- Systems Neuroscience
Background:
- Neural populations exhibit complex dynamics influenced by external inputs.
- Traditional models often overlook the impact of these inputs on neural activity and behavior.
- Understanding intrinsic neural dynamics is crucial for explaining behavior.
Purpose of the Study:
- Introduce BRAID, a deep learning framework to model nonlinear neural dynamics.
- Explicitly incorporate external inputs into neural population models.
- Disentangle intrinsic neural dynamics from input effects to improve behavioral prediction.
Main Methods:
- Developed BRAID, a deep learning framework using input-driven recurrent neural networks.
- Incorporated a forecasting objective to disentangle dynamics from inputs.
- Utilized a multi-stage optimization scheme to prioritize behavior-related intrinsic dynamics.
- Validated with nonlinear simulations and applied to motor cortical activity data.
Main Results:
- BRAID accurately learns intrinsic dynamics shared between neural and behavioral data in simulations.
- Applying BRAID to motor cortical activity improved data fitting by incorporating sensory stimuli.
- The framework enhanced forecasting of neural-behavioral data compared to baseline methods.
Conclusions:
- BRAID offers a novel approach to modeling neural dynamics by integrating external inputs.
- The method effectively disentangles intrinsic dynamics from input influences.
- BRAID improves the understanding and prediction of neural activity and behavior.
Related Concept Videos
01:25Neural Circuits
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
01:22Multi-input and Multi-variable systems
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...
In the absence of...
01:25Modeling with Differential Equations
Population dynamics can be described mathematically by considering the population size P(t) as a function of time. The rate of change of the population is then represented by the derivative of P(t). A simple assumption is that the rate of growth is proportional to the size of the population itself. This leads to an exponential growth model, where the population increases rapidly without bound. While this is a useful first approximation, it does not reflect realistic long-term...