# Artificial Intelligence Stack Exchange Community Digest

## Top new questions this week:

### Is there an argument against using the (reviewed) predictions of a model as ground truth to further train exactly this model?

I plan to use my predictions as ground truth to continue training my model. These predictions are of course reviewed during this process. Is there an argument against that (reinforcement of slight ...

datasets overfitting transfer-learning data-labelling faster-r-cnn
 asked by thzu Score of 7
 answered by R.M. Score of 5

### Does pairing children with their parents cause any harm (in a genetic program)?

If you pair parents with their children (with a cross-over) does this prevent making individuals which are more fit or does this cause other side effects which are harmful to the genetic process? I ...

reference-request genetic-algorithms fitness-functions genetic-programming crossover-operators

### Is Q-learning only capable of learning a deterministic policy?

I was following a reinforcement learning course on coursera and in this video at 2:57 the instructor says Expected SARSA and SARSA both allow us to learn an optimal $\epsilon$-soft policy, but, Q-...

reinforcement-learning q-learning policies sarsa deterministic-policy
 asked by ketan dhanuka Score of 2
 answered by nbro Score of 7

### Is Reinforcement Learning with only feedback on a single action possible?

Consider the following case: A reinforcement based web-crawler where: State = current page + 1 out-link (reduced to features of some sort) Action = Whether to visit that out-link or not (n_actions = ...

reinforcement-learning deep-rl
 asked by Kroshtan Score of 2

### ML algorithm suggestion for databases that change a lot with time after model training

I have a classification problem and I'm using a logistic regression (I tested it among other models and this one was the best). I look for information from game sites and test if a user has the ...

machine-learning classification binary-classification logistic-regression
 asked by Marcos Almeida Score of 1
 answered by former_Epsilon Score of 1

### How to find the order in which DFS algorithm will inspect the nodes?

I have been taking Artificial Intelligence course in College. I came upon this problem. Now here I have to find the order in which DFS algorithm inspects the nodes and what is the path from Start to ...

search path-finding depth-first-search
 asked by astraltrinity Score of 1
 answered by Oliver Mason Score of 0

### Can the state transition function be dynamic in reinforcement learning?

In general, there are two types of transition functions in reinforcement learning. Mathematically, they are as follows #1: Stochastic state transition function: T : S \times A \times S \rightarrow [...

reinforcement-learning markov-decision-process transition-model
 asked by hanugm Score of 1
 answered by Neil Slater Score of 1

## Greatest hits from previous weeks:

### How do I compute the structural similarity between sentences?

I am working on a problem where I need to determine whether two sentences are similar or not. I implemented a solution using BM25 algorithm and wordnet synsets for determining syntactic & ...

natural-language-processing python similarity
 asked by Shubham Tiwari Score of 13
 answered by Oliver Mason Score of 2

### Why does the transformer do better than RNN and LSTM in long-range context dependencies?

I am reading the article How Transformers Work where the author writes Another problem with RNNs, and LSTMs, is that it’s hard to parallelize the work for processing sentences, since you have to ...

machine-learning natural-language-processing recurrent-neural-networks long-short-term-memory transformer
 asked by DRV Score of 44
 answered by Edoardo Guerriero Score of 39

### What is a Dynamic Computational Graph?

Frameworks like PyTorch and TensorFlow through TensorFlow Fold support Dynamic Computational Graphs and are receiving attention from data scientists. However, there seems to be a lack of resource to ...

neural-networks
 asked by Blaszard Score of 25
 answered by Douglas Daseeco Score of 10

### What is a fully convolution network?

I was surveying some literature related to Fully Convolutional Networks and came across the following phrase, A fully convolutional network is achieved by replacing the parameter-rich fully ...

machine-learning convolutional-neural-networks computer-vision image-segmentation fully-convolutional-networks
 asked by PyWalker27 Score of 12
 answered by nbro Score of 13

### What are the limitations of the hill climbing algorithm and how to overcome them?

What are the limitations of the hill climbing algorithm? How can we overcome these limitations?

algorithm search optimization problem-solving hill-climbing
 asked by Abbas Ali Score of 10
 answered by Ugnes Score of 6

### What is the difference between a stochastic and a deterministic policy?

In reinforcement learning, there are the concepts of stochastic (or probabilistic) and deterministic policies. What is the difference between them?

reinforcement-learning comparison policies deterministic-policy stochastic-policy
 asked by nbro Score of 7
 answered by nbro Score of 11

### In a CNN, does each new filter have different weights for each input channel, or are the same weights of each filter used across input channels?

My understanding is that the convolutional layer of a convolutional neural network has four dimensions: ...

convolutional-neural-networks weights filters
 asked by Ryan Chase Score of 59
 answered by Mohsin Bukhari Score of 25

## Can you answer these questions?

### Why do we use the same parameters for the joint, marginal and conditional distributions in VAEs?

I've noticed in several resources on variational autoencoders (for example the wikipedia article), we use the same parameters theta for the prior, likelihood, posterior, etc distributions. For example ...

 asked by Marko Score of 1

### Why does the average-reward estimator for continuing tasks use the TD error?

In Sutton and Barto's RL book, section 10.3 describes how to use average reward $r(\pi)$ to define the quality of a policy, re-defining action-value function $q_\pi(s,a)$ and value function $v_\pi(s)$ ...

reinforcement-learning deep-rl rewards function-approximation sutton-barto
 asked by vaporK Score of 2
You're receiving this message because you subscribed to the Artificial Intelligence community digest.
Unsubscribe from this community digest       Edit email settings       Leave feedback       Privacy

Stack Overflow, 110 William Street, 28th floor, New York, NY 10038

 <3