### How to consider different size of input for “Graph Conv Network”

I’m a student who just start study deep learning. I hope to practice with simple project using Graph Convolution Network. The question is that “How can I handle with different size of input graph for GCN?” Padding with zero is the only way to handle this problem? And zero padding like CNN is proper also…

### Designing a reinforcement learning AI for a game of connect 4

I’ve made a connect 4 game in javascript, and I want to design an AI for it. I made a post the other day about what output would be needed, and I think I could use images of the board and a CNN. I did some research into Reinforcement learning, and I think that’s what…

### How can I train a neural network to detect subliminal messages?

Is there a way to train a neural network to detect subliminal messages? Where can I find the dataset on which to train the neural network? If I have to create the dataset, how would I go about it?

### Relationship between training accuracy and validation accuracy

During model training, I noticed various behaviour in between training and validation accuracy. I understand that ‘The training set is used to train the model, while the validation set is only used to evaluate the model’s performance…’, but I’d like to know if there is any relationship between training and validation accuracy and if yes,…

### How to get layers outputs during training at each mini-batch?

The method model.fit() is used to train the neural network. How can I get the output from any hidden layer during training?

### Does adding a constant to all rewards change the set of optimal policies in episodic tasks?

I’m taking a Coursera course on Reinforcement learning. There was a question there that wasn’t addressed in the learning material: Does adding a constant to all rewards change the set of optimal policies in episodic tasks? The answer is Yes – Adding a constant to the reward signal can make longer episodes more or less…

### Why is stationary sate distribution independent of initial state in policy gradient theorem proof?

I was going through the proof of the policy gradient theorem here: https://lilianweng.github.io/lil-log/2018/04/08/policy-gradient-algorithms.html#svpg In the section “Proof of Policy Gradient Theorem” in the block of equations just under the sentence “The nice rewriting above allows us to exclude the derivative of Q-value function…” they set $$\eta (s) = \sum^\infty_{k=0} \rho^\pi(s_0 \rightarrow s, k)$$…

### What ML algorithms would you suggest in fraud detection?

There are a lot of ML algorithms suggested for fraud detection. Now, I have not been able to find a general overview for all of them. My goal is to create this overview. What algorithms would you suggest and why?

### How are inputs passed to the neural network during the training session?

Sorry if this is a dumb question but I’m really confused. Let’s suppose we have to train a neural network for xor classification task. Are inputs (00, 01, 10, 11) inserted in a sequential way? For example, we first insert the 00 and change the weights, then the 01 and again slightly change them etc.…

### MCTS: How to choose the final action from the root

When the time allotted to Monte Carlo tree search runs out, what action should be chosen from the root? The original UCT paper says bestAction in their algorithm. Monte-Carlo Tree Search: A New Framework for Game AI by Guillaume Chaslot, Sander Bakkes, Istvan Szita, Pieter Spronck says The game action finally executed by the program…