jhielson
commented
1 year ago Hi,
You don't need to worry about that. The GA is responsible to load the weights every time a new genotype or individual needs to be tested. This file should not be changed.
Best regards, Jhielson Montino Pimentel
Get Outlook for Androidhttps://aka.ms/AAb9ysg
From: ewanrego @.> Sent: Friday, November 18, 2022 10:31:54 AM To: jhielson/robotics_GA @.> Cc: Subscribed @.***> Subject: [jhielson/robotics_GA] Question on mpl.py file regarding weights (Issue #1)
This email was sent to you by someone outside the University. You should only click on links or attachments if you are certain that the email is genuine and the content is safe.
mlp.py
Here layer weights are assigned to zeros.
self.weights = [] for i in range(n-1): self.weights.append(np.zeros((self.layers[i].size, self.layers[i+1].size)))
Here dot product of weights and inputs will be always zeros from hidden layers to output layers since there is no bias.
Propagate from layer 0 to layer n-1 using sigmoid as activation function for i in range(1,len(self.shape[0])): # Propagate activity self.layers[i][...] = sigmoid(np.dot(self.layers[i-1],self.weights[i-1])
Are we supposed to handle this in our coursework? Thanks
— Reply to this email directly, view it on GitHubhttps://github.com/jhielson/robotics_GA/issues/1, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AAQ66KHULPNR4JZC6VTULR3WI5LJVANCNFSM6AAAAAASEK2YCA. You are receiving this because you are subscribed to this thread.Message ID: @.***>
The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. Is e buidheann carthannais a th’ ann an Oilthigh Dhùn Èideann, clàraichte an Alba, àireamh clàraidh SC005336.
ewanrego
ignore