JackKelly / neuralnilm_prototype

MIT License
51 stars 22 forks source link

Try quantising input data OR using linspace to init weights #38

Open JackKelly opened 9 years ago

JackKelly commented 9 years ago

See if this means we can get performance like e59a, but without one or both of the first dense layers.

Also try using linspace to init weights of first layer. And try visualisation to see what those neurons are doing (#15)