8 votes

How is ChatGPT able to repeat random numbers?

As well as decent modelling of purposes or strings of digits, ChatGPT can identify when a completely novel string might be a product name, a fictional person or place etc. The language model in ...
  • 25.4k
5 votes

How does chatGPT know it's an AI?

Unlike GPT-2/3 (and other language models around, such as OPT, PaLM, and BLOOM), it is trained not only on the texts downloaded from the Internet. After pre-training on purely textual data (OpenAI ...
  • 231
5 votes

Does chatGPT learn or remember from (public) user input? Will it 'fess up to it? I could not get it to reveal

ChatGPT does not answer to just your last question, but to the whole dialog. It tries to continue the dialog in a way that has the same structure as the gigabytes of other texts it has studied. GPT-3 ...
  • 151
2 votes

How to deal with varying number of input images?

There are are couple methods that you may wish to consider for this challenging but interesting problem. In some cases, multiple images are captured because of artifacts in the initial images, so ...
2 votes

How should I train the players in the game of tag?

I was able to make the game work and because of that I can say that the GA approach at least makes some sense. I did the following changes: Added crossover Increased generation size from 50 to 300 ...
  • 143
2 votes
Accepted

How should I train the players in the game of tag?

Your approach should work in general, but there are a lot of key details that will make the difference between success and failure. The most major issue is a number of hyperparameters that you have ...
  • 25.4k
2 votes
Accepted

Please help me understand the role of loss function in neural networks

I think you are confused about the terms error, loss function and metric. To summarize: Error (vector) tells us how off each prediction is. Loss function maps the error (vector) to a single number (...
  • 160
1 vote

Please help me understand the role of loss function in neural networks

There are different functions to pick from for your loss. The most common read online is the Mean Squared Error. It calculates how far the prediction is off from the actual value and squares it. All ...
1 vote

Do different architectures really make a difference or is it just a matter of the training process?

The answer might be based on opinion, but yes it matters. The concept is called Exploration vs Exploitation. Consider that you are standing on the top of a hill and you need to go down to the foot. ...
1 vote
Accepted

What is the correct loss function for binary classification: Cross entropy or Binary cross entropy?

Binary cross-entropy loss is a specific case for cross-entropy loss. Theoretically, one can also use the normal cross-entropy loss for binary classification. Binary cross-entropy is probably ...
1 vote

Single Layer Perceptron Backpropagation: How to compute affect of the net value on the output?

is always wrong. Most implementations then "silently" correct this error, even if the docstrings have this wrong variant, in the actual use it is done correctly. and 3. are the same, ...
1 vote

Is there a way to see the feature importance in deep learning (neural networks)?

In the current state, Deep learning for Tabular is not very popular, so it is very hard to find libraries that support feature importance. However, TabNet also provides the ...
1 vote
Accepted

Should a CNN generalize to arbitrary positions in the data?

You would expect the model to extrapolate due to the 1D-Convolutions and the pooling, because they are translation equivariant (with local invariance due to the pooling). Thus, these layers produce ...
  • 1,157
1 vote
Accepted

Is it possible to build a facial recognition system using a multi-layered DNN?

Yes, it is totally possible. It's useful to fully understand the math and functionality of NN's. Additionally, if doing it correctly, your whole DNN should only make up to a few hundred lines of code. ...
1 vote

How are NNs output setup for games that allow multiple actions each turn and have very large sets of possible actions?

I participated in this contest and ended up 30th (out of ~4500). I used mainly neural network. I split the problem into parts: for each my own cell, I ask the NN what to do (build, spawn, move) ...
  • 96
1 vote

Neural network: Initial weights for layer with non-negative constraint

I, unfortunately, cannot provide you with a scientifically based answer, so I'll try to logic my way to an answer. I know that there are things called 'nonnegativity-constrained autoencoders'. I do ...

Only top scored, non community-wiki answers of a minimum length are eligible