Are there any strategies that would help me visualize the ‘behavior space’ and make a novelty function?

In “Abandoning Objectives: Evolution through the Search for Novelty Alone”, it is explained how the novelty search is a function that is domain specific, depending on the differing behaviors that can potentially emerge. The primary test is a deceptive maze and it seems like they define novelty as a function that is dependent on each…

AdamOptimizer minimize function not updating weights

I am trying to implement an actor-critic algorithm. I am using AdamOptimizer from tensorflow. The thing is, when i replace “self.opt.minimize” with “self.opt.compute_gradients”, the gradients i get are not zeros. But when i use “self.opt.minimize”, when i check the weights of my NN before and after the update, the weights are the same, they are…

Imposing contraints on sequence of image classifications

Are there example implementations of networks that apply constraints across sequences of image classifications where class labels are ordinal numbers? For example, to cause the output of a CNN to monotonically increase across frames, where the number may increase either more or less steeply but only in one direction across the entire sequence, or as…

Are there any approaches other than deep learning to achieve better performance for a question answering bot?

I’m working on a question answering bot as my graduation project. The main concept is having a text file with many sentences, and building a question answering bot which answers a user’s question based on the text file in hand. Until now I used TF-IDF and Cosine Similarity and the results are somewhat satisfactory. The…