Questions tagged [artificial-intelligence]

Question 1

I am trying to understand how the Reduce Operation that PyTorch does in its backward pass for broadcasted tensors actually work under the hood. I am trying to make a cpp library for neural networks ...

Question 2

I'm building a U-Net for predicting density maps. The ground truth maps are generated by labeling centroids in the objects of interest in the original image (they are all of the same class), forming a ...

Question 3

Let us say that in the not-so-distant future, people might have to convince an LLM that they are worthy of a job. Is it possible to use prompt injection to convince the LLM that you are worthy of a ...

Question 4

I gave this prompt to ChatGPT o3-mini-high: Give me a novel algorithm not discovered yet that reduces the complexity of matrix multiplication. Do you think this algorithm is correct and truly novel? ...

Question 5

So I am building a CNN from scratch. I built all the layers with the first layer of convolution->pooling, the second layer of convolution->pooling, flatten, feed into a deep network (built that ...

Question 6

I would like to implement a genetic algorithm to solve the matchmaking problem between offers and demands in a marketplace. I found a research paper which proposes the following encoding: each ...

Question 7

I struggle with the understanding of this algorithm. Is there anybody willing to explain me how the tree is built in RETE and how it helps with concrete inputs?

Question 8

Even if it may be complicated, is it possible with the present technology?

Question 9

In the GT (Graph Transformer) model presented by Dwivedi & Bresson in "A Generalization of Transformer Networks to Graphs", the following equations are used to update node and edge ...

Question 10

I have a bunch of transcripts from online videos but I suspect the transcripts aren't formatted well. There are no punctuations, sentences are broken abruptly, some words aren't complete (for example ...

Question 11

Can we assume that a 7gb llm model knows 7gb of text info? (by 7gb i mean a 7 billion parameter model at Q8 quantization) or a (1.75 billion parameter model at full fp32 precision) For example, a 70,...

Question 12

I was studying AI and when a question came to my mind. I know that one of the objections to the possibility of a thinking machine examined by Turing is the so called mathematical objection, ...

Question 13

In this post I asked about why the sigmoid/softmax function was used in classification: Binary Classification- Non-Differentiable Loss Function But I have a followup question: We're assuming that the ...

Question 14

A lot of AI hardware coming out lately has its performance mentioned in TOPS i.e trillion operations per second. Does anyone have an Idea how to estimate the llm performance on such hardware in tokens ...

Question 15

For binary classification using linear regression, we pass the output z of the linear regression through the sigmoid function so that if the linear regression takes an input x which should be ...

Stack Exchange Network

Questions tagged [artificial-intelligence]

Understanding reduce operations in PyTorch and autodiff. Confused on Operation tracking

When predicting density maps with CNNs: is using MSE more appropiate than pixelwise sigmoid activation + binary cross entropy?

Can prompt injection be used to circumvent the intended use of LLM's?

Algorithm Discovery Using ChatGPT O3-mini-high?

Training A Convolutional Neural Network

I need help in designing a genetic algorithm for matchmaking in ecommerce

How does the RETE algorithm for expert production systems work?

Is there any way to program a chess bot which never loses?

Simplest way to incorporate edge types into self-attention (in a graph transformer)?

Forming Sentences

How much do llms know?

Gödel's theorem and machines' power

linear relationship between the log-odds and the features

TOPS trillion operations per second to Tokens per second

Binary Classification- Non-Differentiable Loss Function

Hot Network Questions