Search

We investigate a method, weighted average model fusion, that enables neural networks to learn from the experiences of other networks, as well as from their own experiences. This method is inspired by the the social natural of humans, which has been shown to be one of the biggest factors in the development of our cognitive abilities. Modern machine learning has focuses predominantly on learning from direct training, and has largely ignored learning through social engagement with peers, neural networks will the same topology. In order to explore learning through engagement with peers, we have created a way for neural networks to teach each other. Our method allows neural networks to exchange knowledge by combining their weights. It calculates a pairwise weighted average of the weights of two neural networks, and then replaces the existing weight with the new value. We find that weighted average model fusion successfully enables neural networks to learn from the experiences of their peers and combine it with the knowledge that is gained from its own individual experiences. Additionally, we explore the effects that several meta-parameters have on model fusion to provide deeper insights into how the behaves in a variety of scenarios.

Benjamin Reeves and Gwendolyn Murphy struggle through a life of twists and turns to finally change the world together...and they did it by their Choices.

Director's reports for 1883-1886 and 1891. Each report is of 4 pages. The reports deal with prospecting in Tasmania. Prospectors James Rowe and Mr Hodgkinson are mentioned. Also included is a notice (29 Jan. 1892) that an extraordinary general meeting is to be held on 10 Feb. 1892 to examine a resolution that the company be voluntary wound up. Another notice (20 Feb. 1892) from the company to the effect that an extraordinary general meeting be held for the resolution that the company be wound up can be submitted for confirmation as a special resolution. The secretary of the company is W. Brookes. The directors are Thomas Dyer Edwards, Jun.; William Hy. Gramshaw; Charles George Hale; Joshua Hutchinson; Thomas James Reeves.