Artificial Intelligence Stack Exchange Community Digest

Top new questions this week:

Why is a bias parameter needed in neural networks?

I have read several resources, including previously asked questions such as this. I have also read arguments related to intercepts needed to separate linearly separable data. If my neural network can …

neural-networks deep-learning feedforward-neural-networks

asked by SajanGohil Score of 12 answered by David Hoelzer Score of 14

Will a CNN that is Group Equivariant always be better than a regular CNN?

I am reading this paper about Group Equivariant Convolutional Networks. Basically, it is a CNN whose construction makes the network naturally equivariant to Group transformations (e.g. rotations) of …

convolutional-neural-networks

asked by puradrogasincortar Score of 5 answered by Dennis Soemers Score of 7

Can LSTM model use ReLU or LeakyReLU as the activation funtion?

Can LSTM model use ReLU or LeakyReLU as the activation funtion? If so, when should one use tanh and when should one use ReLU or LeakyReLU?

training long-short-term-memory activation-functions

asked by BlueSnake Score of 1 answered by Brian O'Donnell Score of 1

What is meant by “Deep Learning models are not understood”?

It is a sentence that I hear a lot and I guess I don’t get what it means. It seems that the weight optimization procedure is very well understood and there is, to some extent, theoretical/empirical …

deep-learning philosophy agi

asked by benr Score of 1 answered by chessprogrammer Score of 2

How is ChatGPT trained?

According to OpenAI, ChatGPT is trained in a 3-step process. Are the steps where human AI trainers are involved, i.e. training the initial policy and providing the A>B>C>D grading as …

machine-learning chatgpt

asked by Meatball Princess Score of 1 answered by Rexcirus Score of 1

How to detect outlier images?

Before I describe my challenge, I want to point out that I have searched extensively online for “outlier image detection”, “anomaly images detection”, etc., but all returned …

computer-vision image-recognition anomaly-detection

asked by pookie Score of 1 answered by Triple S Score of 3

Best feature engineering approach for interest-based age classification

I have a dataset which has users (rows) with the list of their interests (IABs), which looks like this …

machine-learning classification feature-selection feature-engineering

asked by theodre7 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

How do I handle large images when training a CNN?

Suppose that I have 10K images of sizes $2400 \times 2400$ to train a CNN. How do I handle such large image sizes without downsampling? Here are a few more specific questions. Are there any …

neural-networks deep-learning image-recognition convolutional-neural-networks

asked by WaterRocket8236 Score of 25 answered by Maxim Score of 22

Why do we need explainable AI?

If the original purpose for developing AI was to help humans in some tasks and that purpose still holds, why should we care about its explainability? For example, in deep learning, as long as the …

philosophy social explainable-ai

asked by malioboro Score of 69 answered by Djib2011 Score of 75

Can LSTM neural networks be sped up by a GPU?

I am training LSTM neural networks with Keras on a small mobile GPU. The speed on the GPU is slower than on the CPU. I found some articles that say that it is hard to train LSTMs (and, in general, …

training tensorflow keras long-short-term-memory gpu

asked by Dieshe Score of 8 answered by Dieshe Score of 5

What is the difference between strong-AI and weak-AI?

I’ve heard the terms strong-AI and weak-AI used. Are these well defined terms or subjective ones? How are they generally defined?

terminology definitions agi comparison narrow-ai

asked by WilliamKF Score of 44 answered by jrmyp Score of 38

How could artificial intelligence harm us?

We often hear that artificial intelligence may harm or even kill humans, so it might prove dangerous. How could artificial intelligence harm us?

philosophy social neo-luddism

asked by Manak Score of 55 answered by Djib2011 Score of 52

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 63 answered by Mohsin Score of 27

Can you answer these questions?

Why does the pass@k metric not “behave like” probability?

pass@k is a metric used to evaluate models that generate code, used for example to evaluate Codex. To evaluate pass@k, you have a dataset of natural language/code pairs, and you pass each NL prompt to …

transformer

asked by Jack M Score of 1

Dimensionality Limitations

I just started learning about AI and have been reading a book called “Foundations of Machine Learning” by Mehryar Mohri so that I can try to create my own. I had a question come up recently: …

dimensionality-reduction curse-of-dimensionality

asked by Sophia Score of 1

Prioritized experience replay correction with off-policy estimators

Prioritized exeperience replay (PER) biases the sampling and introduces importance sampling (IS) correction to the Q-function update. Weights are $w = \frac{1}{N P}^\beta$, where $N$ is the batch size …

reinforcement-learning off-policy-methods experience-replay

asked by Simon Score of 1