You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
what is the way of training multiple neural-nets in universal ODEs . Do we train them together (if yes , how ?) or do we train them subsequently ?
NN_1 =FastChain(FastDense(2,32,tanh), FastDense(32,32,tanh),FastDense(32,1))
p1 =initial_params(NN_1)
NN_2 =FastChain(FastDense(2,32,tanh), FastDense(32,32,tanh),FastDense(32,1))
p2 =initial_params(NN_1)
functiondudt_(u, p,t)
x, y, z = u
z1 =NN_1([x,y],p1)
z2 =NN_2([y,z],p2)
[p_[1]*x + z[1],
-p_[3]*y + z[2],
p_[4]*z - z[1] - z[2]
]
end# where p_[1], p_[3],p_[4] are known parameters passed through p
prob_nn =ODEProblem(dudt_,u0, tspan, p)
sol_nn =solve(prob_nn)
functionpredict() # etc..etcfunctionloss()
How do I update/ train NN_1 and NN_2 together using say sci_ml if thats how I should proceed ?
The text was updated successfully, but these errors were encountered:
yewalenikhil65
changed the title
training methods multiple neural-nets in universal ODEs
training method for multiple neural-nets in universal ODEs
Dec 15, 2020
what is the way of training multiple neural-nets in universal ODEs . Do we train them together (if yes , how ?) or do we train them subsequently ?
How do I update/ train NN_1 and NN_2 together using say
sci_ml
if thats how I should proceed ?The text was updated successfully, but these errors were encountered: