A typical artificial neural network (ANN) is traditionally trained using stochastic gradient descent (SGD). However, it is unlikely that a real biological neural network is trained similarly. Neuroscience theories, such as Hebbian Theory could inspire adaption from the traditional training method SGD to make ANNs more biologically plausible. This research will propose a method, called the Hebbian Plasticity Term (HPT) method, that incorporates the mathematical description of Hebbian theory to modify the traditional training method SGD. The influence of the hebbian plasticity term ϕ on SGD shows more biologically realistic plasticity of a synaptic connection between neurons in the ANN at the cost of performance.
The Research Project is a research project that serves as an exercise for the master’s thesis. As such it serves to give master students who did their bachelor study elsewhere the experience that bachelor students from the UT obtained during their bachelor project.
View the full research paper for this project.
A typical artificial neural network (ANN) is traditionally trained using stochastic gradient descent (SGD). However, it is unlikely that a real biological neural network is trained similarly. Neuroscience theories, such as Hebbian Theory could inspire adaption from the traditional training method SGD to make ANNs more biologically plausible. This research will propose a method, called the Hebbian Plasticity Term (HPT) method, that incorporates the mathematical description of Hebbian theory to modify the traditional training method SGD. The influence of the hebbian plasticity term ϕ on SGD shows more biologically realistic plasticity of a synaptic connection between neurons in the ANN at the cost of performance.
The Research Project is a research project that serves as an exercise for the master’s thesis. As such it serves to give master students who did their bachelor study elsewhere the experience that bachelor students from the UT obtained during their bachelor project.
View the full research paper for this project.