Artificial Intelligence Stack Exchange Community Digest

Top new questions this week:

Why are policy gradient methods more effective in high-dimensional action spaces?

David Silver argues, in his Reinforcement Learning course, that policy-based reinforcement learning (RL) is more effective than value-based RL in high-dimensional action spaces. He points out that the …

policy-gradients value-functions function-approximation softmax value-based-methods

asked by Saucy Goat Score of 4 answered by mohottnad Score of 2

What causes ChatGPT to generate responses that refer to itself as a bot or LM?

ChatGPT occasionally generates responses to prompts that refer to itself as a “bot” or “language model.” For instance, when given a certain input (the first paragraph of this …

chat-bots training-datasets language-model gpt-3 chat-gpt

asked by Obie 2.0 Score of 4

What's the relationship between number of heads and embedding dimension in Transformers?

I am reading the book: Natural Language Processing with Transformers. It has the following paragraph Although head_dim does not have to be smaller than the number of embedding dimensions of the …

deep-learning natural-language-processing transformer attention hyper-parameters

asked by desert_ranger Score of 3 answered by p0p4k Score of 0

What if each sample was normalized on its own before sending them to the neural network?

The standard method is to normalize the entire dataset (the training part) then send it to the model to train on. However I’ve noticed that in this manner the model doesn’t really work well when …

neural-networks normalisation

asked by Maks Score of 3 answered by besterma Score of 3

Pytorch's Actor-critic implementation seems to be implemented in a Monte-Carlo fashion – why?

In the Actor-Critic example, provided by PyTorch, it seems that the update rule only occurs when the episode ends (like in a Monte-Carlo process). Specifically, in their …

reinforcement-learning pytorch actor-critic-methods

asked by Hadar Sharvit Score of 2 answered by Hadar Sharvit Score of 1

In what circumstances can we replace the max operator with random selection in the DQN?

In the original DQN paper, gradients during training are derived as follows: $\nabla_{\theta_i} L_i\left(\theta_i\right)=\mathbb{E}_{s, a \sim \rho(\cdot) ; s^{\prime} \sim \mathcal{E}}\left[\left(r+\…

reinforcement-learning dqn

asked by bonzo_pippinpaddle Score of 1

How can a language model keep track of the provenance of the main knowledge/sources used to generate a given output?

One of the main criticisms against the use of ChatGPT on stack exchange is that it doesn’t attribute the main knowledge/sources used to generate a given output. How can a language model keep track of …

natural-language-processing language-model chat-gpt

asked by Franck Dernoncourt Score of 1 answered by Franck Dernoncourt Score of 1

Greatest hits from previous weeks:

How to classify data which is spiral in shape?

I have been messing around in tensorflow playground. One of the input data sets is a spiral. No matter what input parameters I choose, no matter how wide and deep the neural network I make, I cannot …

neural-networks machine-learning tensorflow regression

asked by Souradeep Nanda Score of 15 answered by Salvador Dali Score of 14

What is the difference between artificial intelligence and machine learning?

These two terms seem to be related, especially in their application in computer science and software engineering. Is one a subset of another? Is one a tool used to build a system for the other? What …

machine-learning comparison terminology ai-field

asked by intcreator Score of 98 answered by miku Score of 63

What is an objective function?

Local search algorithms are useful for solving pure optimization problems, in which the aim is to find the best state according to an objective function. My question is what is the objective function?

terminology objective-functions optimization local-search meta-heuristics

asked by Abbas Ali Score of 5 answered by nbro Score of 6

What is the difference between simple reflex and model-based agents?

What is the difference between simple reflex and model-based agents? What is the role of the internal state in the case of model-based agents?

comparison intelligent-agent simple-reflex-agents

asked by Pierre P. Score of 5 answered by quintumnia Score of 4

Can a neural network be used to predict the next pseudo random number?

Is it possible to feed a neural network the output from a random number generator and expect it learn the hashing (or generator) function, so that it can predict what will be the next generated pseudo-…

neural-networks machine-learning deep-learning prediction randomness

asked by AshTyson Score of 27 answered by Demento Score of 19

What are the advantages of ReLU vs Leaky ReLU and Parametric ReLU (if any)?

I think that the advantage of using Leaky ReLU instead of ReLU is that in this way we cannot have vanishing gradient. Parametric ReLU has the same advantage with the only difference that the slope of …

neural-networks activation-functions relu

asked by gvgramazio Score of 19 answered by Douglas Daseeco Score of 13

How do neural networks play chess?

I have been spending a few days trying to wrap my head around how and why neural networks are used to play chess. Although I know very little about how the game of chess works, I can understand the …

neural-networks reference-request chess board-games

asked by stats_noob Score of 18 answered by Neil Slater Score of 16

Can you answer this question?

Is it possible to create an AI that produces output without giving it input?

AFAIK an AI is first trained using a data set of input and output values. After the training proccess you can give the AI input and it will produce output. For example when you write a sentence to an …

chat-bots training-datasets

asked by zomega Score of 1