Artificial Intelligence Stack Exchange Community Digest

Top new questions this week:

How does ChatGPT retain the context of previous questions?

One of the innovations with OpenAI’s ChatGPT is how natural it is for users to interact with it. What is the technical enabler for ChatGPT to maintain the context of previous questions in it’s answers?…

natural-language-processing gpt-3

asked by milez Score of 4

Training tricks to improve stability of mixed precision

I would love to be able to use automatic mixed precision more extensively in my training, but I find that it is too unstable and often ends in NaNs. Are there any general tricks in training that …

training precision

asked by Luke Score of 2

My cross entropy loss gradient calculation is wrong according to the answer key

Given a neural network model for Covid-19 classification with $C=1$ for positive and $C=0$ for negative Let $x_1 = 6$ and $x_2=2$ find Probability if the patient got Covid-19 $p\left(C=1 | x; w,b\…

neural-networks homework

asked by Airlangga Fidiyanto Score of 2 answered by mohottnad Score of 4

Why should one expect the backward pass to take twice as long as the forward pass?

I have seen it stated that, as a rule of thumb, a backward pass in a neural network should take about twice as long as the forward pass. Examples: From DeepSpeed’s Flops Profiler docs, the profiler: …

neural-networks backpropagation deep-neural-networks

asked by user26866 Score of 2 answered by user26866 Score of 0

How can an Artificial Intelligence system be ethically trained to generate art?

There have been a lot of popular AI-generating image systems put out recently, with such systems as Midjourney and Dall-E catching attention with how well put-together many of the automatically …

image-generation ethics

asked by Mithical Score of 1 answered by Robin van Hoorn Score of -1

Phonetic similarity metric for NLP (English)

I am looking for similarity metrics of phonemes (expressed in IPA) in English. In other words, given two phonemes A and B (both written), I want to know how similar they are based on some metric, M. …

natural-language-processing

asked by postnubilaphoebus Score of 1 answered by Oliver Mason Score of 0

Basic principles of a single player search

there is a grid 8 by 8, filled with all 12 pentominos and a free area 4 by 3, the player must use an area 2 by 2 and must escape at bottom left in minimum handlings of pentominos, 10.000 level …

training search

asked by wilfree Score of 1

Greatest hits from previous weeks:

What is non-Euclidean data?

What is non-Euclidean data? Here are some sub-questions Where does this type of data arise? I have come across this term in the context of geometric deep learning and graph neural networks. …

deep-learning definitions geometric-deep-learning graph-neural-networks non-euclidean-data

asked by nbro Score of 23 answered by brazofuerte Score of 13

Is “AIAngel” (Patreon) a fake?

These guys here: www.patreon.com/AiAngel are saying that they’ve created a AI who can chat and stream. As the so-called administrator “Rogue” said: this chat/streamer bot are no fake. Also, …

chat-bots turing-test ai-hoaxes

asked by M.N.Raia Score of 7 answered by Ess Kay Score of 5

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 60 answered by Mohsin Bukhari Score of 25

Where can I find the original paper that introduced RNNs?

I was able to find the original paper on LSTM, but I was not able to find the paper that introduced “vanilla” RNNs. Where can I find it?

recurrent-neural-networks long-short-term-memory reference-request papers

asked by Ahsan Tarique Score of 16 answered by David Nemeskey Score of 11

What is self-supervised learning in machine learning?

What is self-supervised learning in machine learning? How is it different from supervised learning?

machine-learning comparison supervised-learning self-supervised-learning representation-learning

asked by nbro Score of 91 answered by nbro Score of 90

How do I choose the optimal batch size?

Batch size is a term used in machine learning and refers to the number of training examples utilised in one iteration. The batch size can be one of three options: batch mode: where the batch size is …

neural-networks machine-learning training stochastic-gradient-descent batch-size

asked by Sebastian Nielsen Score of 19 answered by Ayoub EL MAJJODI Score of 6

Are there other approaches to deal with variable action spaces?

This question is about Reinforcement Learning and variable action spaces for every/some states. Variable action space Let’s say you have an MDP, where the number of actions varies between states (for …

reinforcement-learning reference-request deep-rl function-approximation action-spaces

asked by Rikard Olsson Score of 24 answered by Dennis Soemers Score of 18

Can you answer these questions?

Benefits of building a multi-GPU PC with consumer cards

I’m building my first PC for ML and I’m a bit lost. My use case is training models like Detectron2 or YOLOv5 on instance segmentation. Please do let me know if I’m overthinking this and those models …

hardware

asked by Nikolay Dyankov Score of 1

Image classification problem with multiple right classes

I have a use case where the model needs to detect fabricdefects. There are 15+ different kinds of defects. In one image there can be multiple defects present. The straight forward solution for this …

classification image-recognition objective-functions multiclass-classification multi-label-classification

asked by Nick De Wispelaere Score of 1 answered by Robin van Hoorn Score of 0