Most Popular

1500 questions
5
votes
2 answers

What layers to use in a Neural Network for card game

I am currently writing an engine to play a card game and I would like for an ANN to learn how to play the game. The game is currently playable, and I believe for this game a deep-recurrent-Q-network with a reinforcement learning approach is the way…
5
votes
1 answer

How do I statistically evaluate a ML model?

I have a model that predicts sentiment of tweets. Are there any standard procedures to evaluate such a model in terms of its output? I could sample the output, work out which are correctly predicted by hand, and count true and false positives and…
schoon
  • 237
  • 2
  • 7
5
votes
3 answers

How can the generalization error be estimated?

How would you estimate the generalization error? What are the methods of achieving this?
5
votes
3 answers

Is it better to make neural network to have hierchical output?

i'm quite new to neural network and i recently built neural network for number classification in vehicle license plate. It has 3 layers: 1 input layer for 16*24(382 neurons) number image with 150 dpi , 1 hidden layer(199 neurons) with sigmoid…
강신욱
  • 105
  • 5
5
votes
1 answer

Can I combine two classifiers that make different kinds of errors to get a better classifier?

I have a dataset with 2,23,586 samples out of which i used 60% for training and 40% for testing. I used 5 classifiers individually, SVM, LR, decision tree, random forest and boosted decision trees. SVM and LR performed well with close to 0.9…
Sudha
  • 51
  • 1
5
votes
1 answer

How would you encode your input vector/matrix from a sequence of moves in game like tasks to train an AI? e.g. Chess AI?

I've seen data sets for classification / regressions tasks in domains such as credit default detection, object identification in an image, stock price prediction etc. All of these data sets could simply be represented as an input matrix of size…
5
votes
1 answer

How could you generate sentences from lists of facts

Let's pretend we had a list of facts (similar to prolog tuples) that define some knowledge about some entities. e.g. doing(clean, data) done(collect, data) todo(train, model) todo(write, paper) What methods could I use to generate sentences…
5
votes
2 answers

Does value iteration still return the true Q-values in stochastic environment?

I'm working with the FrozenLake environment (8x8) from Gymnasium. In the deterministic case (is_slippery=False), I understand that using value iteration can converge to the true Q-values, since the environment is fully observable and transitions are…
5
votes
1 answer

Is PAC-unlearnability a fundamental limitation for LLM reasoning?

For simplicity, let’s focus on knowledge reasoning tasks with Yes/No answers. According to learning theory, even moderately complex knowledge reasoning tasks are PAC-unlearnable. This implies that no learning-based reasoning engine trained on a…
nova
  • 180
  • 6
5
votes
1 answer

How do LLMs tokenize python (significant whitespace)

I was learning about tokenization (WordPiece) and how there is a normalization step prior to that that will remove consecutive whitespace from the input text, since these are not significant normally. But that got we wonder how do LLMs still…
5
votes
2 answers

Is there a conflict between NFL theorem and multimodal learning?

The definition of multimodal learning and NFL theorem is clear to me. My question is, if model good at a specific field might perform badly in another field, is there any need to find out a multimodal model? My current explanation is that for a…
5
votes
1 answer

Is PyTorch's `grad_fn` for a non-differentiable function that function's inverse?

What is grad_fn for a non-differentiable function like slicing (grad_fn=), view (grad_fn=), etc.? Is grad_fn simply the function's inverse operation? Where in the source code can I see the implementation of…
Geremia
  • 555
  • 1
  • 5
  • 12
5
votes
1 answer

Is natural language reasoning the right way to implement reasoning in AI?

It is well known that human reasoning, after evolving for at least several thousand years, has gradually transformed from natural language reasoning to formal reasoning. In modern science, a significant indicator of a discipline's maturity is…
jario
  • 53
  • 5
5
votes
1 answer

Which model would recognize the rotated version of its input without explicit training during inference?

Training an MNIST classifier with a regular ANN will make the model recognize its unrotated version. But is there such a model where I train the unrotated version as usual, but it also recognizes its rotated version, e.g., the 90-degree version,…
5
votes
1 answer

Trying to understand VGG convolution neural networks architecture

Trying to understand the VGG architecture and I have these following questions. I understand the general understanding of increasing filter size is because we are using max pooling and so its image size gets reduced. So in order to keep information…