Artificial Intelligence Stack Exchange Community Digest

Top new questions this week:

Why does Advantage Learning help function approximators?

Many later RL algorithms like PPO or Duelling DQN estimate the advantage. I am not very sure of how that really helps. For instance, the actor loss for a simple actor critic algorithm is given by – <...

reinforcement-learning deep-rl q-learning advantage-actor-critic

asked by desert_ranger Score of 2 answered by pythonic833 Score of 1

GAN : Why does a perfect discriminator mean no gradient for the generator?

In the training of a Generative Adversarial Networks (GAN) system, a perfect discriminator (D) is one which outputs 1 (“true image”) for all images of the training dataset and 0 (“false …

training generative-adversarial-networks loss gradient wasserstein-gan

asked by Soltius Score of 1

What exactly is the future of mathematical analysis that can be dealt with AI (especially in the automated theorem proving)?

As a student of numerical analysis, I can see how mathematical analysis involved in making a language program specifically in the convergence analysis of an approximation method. But, while chatting …

math chatgpt automated-theorem-proving philosophy-of-math

asked by Messi Lio Score of 1 answered by Eduard Score of 2

Computation required for GPT model to choose likely word from n-options where n < total vocabulary size

Let’s imagine two different use cases for a LLM/GPT-3. Predicting the next most likely word in a sequence using all ~50k words in its dictionary (i.e. the standard method of prompting a LLM) Checking …

natural-language-processing math transformer gpt gpt-3

asked by Derek Score of 1

What makes ChatGPT a generative model?

I’m working my way through how ChatGPT works. So I read that ChatGPT is a generative model. When searching for generative models, I found two defintions: A generative model includes the distribution …

machine-learning generative-model probability chatgpt

asked by Ai4l2s Score of 1 answered by Robin van Hoorn Score of 2

Are there any advantages of encoding an image as a graph to use in Graph Convolutional Networks?

I have seen this encoding of an image as a graph: The set of the nodes $V$ is the set of pixels. If the image is of size $10\times10$, then we have $10\cdot10=100$ pixels. Each node has a length 3 …

convolutional-neural-networks computer-vision data-preprocessing graph-neural-networks

asked by puradrogasincortar Score of 1 answered by Chillston Score of 0

High precision and low recall results. What does it mean?

I am working on a classification algorithm for brain rhythms. However, when I implemented the metrics for precision, accuracy, F1 score and recall. My results show that my algorithm has a high …

machine-learning classification testing precision recall

asked by GGChe Score of 1 answered by Dave Score of 1

Greatest hits from previous weeks:

What are the main differences between skip-gram and continuous bag of words?

The skip-gram and continuous bag of words (CBOW) are two different types of word2vec models. What are the main differences between them? What are the pros and cons of both methods?

natural-language-processing comparison word2vec cbow skip-gram

asked by DRV Score of 18 answered by Edoardo Guerriero Score of 23

What exactly is a hidden state in an LSTM and RNN?

I’m working on a project, where we use an encoder-decoder architecture. We decided to use an LSTM for both the encoder and decoder due to its hidden states. In my specific case, the hidden state of …

recurrent-neural-networks long-short-term-memory hidden-layers seq2seq encoder-decoder

asked by user8714896 Score of 10 answered by Eka Score of 9

How can I predict the next number in a non-obvious sequence?

I’ve got an array of integers ranging from -3 to +3. Example: [1, 3, -2, 0, 0, 1] The array has no obvious pattern since it represents bipolar disorder mood swings. What is the most suitable approach …

machine-learning recurrent-neural-networks prediction sequence-modeling

asked by ZenBerry Score of 6 answered by serali Score of 9

What is the credit assignment problem?

In reinforcement learning (RL), the credit assignment problem (CAP) seems to be an important problem. What is the CAP? Why is it relevant to RL?

reinforcement-learning definitions credit-assignment-problem

asked by nbro Score of 23 answered by nbro Score of 32

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

Is it possible to train the neural network to solve math equations?

I’m aware that neural networks are probably not designed to do that, however asking hypothetically, is it possible to train the deep neural network (or similar) to solve math equations? So given the …

neural-networks math applications

asked by kenorb Score of 35 answered by zergylord Score of 24

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

Can you answer this question?

What can unsupervised learning actually be used for and how can humans interpret the outputs?

I am trying to refine my knowledge of AI, but unsupervised learning is a bit of a stumbling block for me. I understand that it finds ‘hidden’ patterns in data, but if they are hidden, how does a user …

unsupervised-learning

asked by Robert Flook Score of 1 answered by Václav Struhár Score of 0