Skip to main content
New
Stack Overflow Jobs powered by Indeed: A job site that puts thousands of tech jobs at your fingertips (U.S. only). Search jobs
13 votes
Accepted

How is it that AI can become biased, and what are the proposals to mitigate this?

Lately with my Google searches, the AI model keeps auto filling the ending of my searches with: “...in Vietnamese” I can see how this would be annoying. I don't think Google's auto-complete algorithm ...
Neil Slater's user avatar
  • 32.4k
5 votes

Can prior knowledge be encoded in deep neural networks?

Neural nets incorporate prior knowledge. This can be done in two ways: the first (most frequent and more robust) is in data augmentation. For example in convolutional networks, if we know that the "...
Foivos's user avatar
  • 176
4 votes

How is it that AI can become biased, and what are the proposals to mitigate this?

Another fallacy that appears common to most search engines is that anything a person searches on is an aspect of their own identity. I once searched on walk-in tubs for a very elderly relative, and ...
Ellie's user avatar
  • 41
4 votes

Can prior knowledge be encoded in deep neural networks?

Yes, we can do it in a deep learner. For example, suppose we have an input vector likes $(a, b)$ and from prior knowledge, we know $a^2 + b^2$ is important too. Hence, we can add this value to the ...
OmG's user avatar
  • 1,816
4 votes

Is algorithmic bias due to the training dataset used?

Just to add to what has already been said in @BlueMoon93's answer: Algorithmic bias is the bias built into the algorithm. Now for the long answer: As stated by the so called No free lunch theorem: ...
Tshilidzi Mudau's user avatar
4 votes

Is algorithmic bias due to the training dataset used?

As the name implies, algorithmic bias is related with the used algorithm. Due to the way it was programmed or devised, the algorithm will be biased in some of its samples. From Communications of the ...
BlueMoon93's user avatar
4 votes

Preventing bias by not providing irrelevant data

Why can't we just feed the training data without data that we would consider discriminatory or irrelevant, for example, without fields for gender, race, etc., can AI still draw those prejudiced ...
naive's user avatar
  • 699
3 votes

How do I keep my system (online) learning if I can get ground truth labels only for examples flagged positive?

A first question that I think is important to consider is: do you expect the data that you're dealing with to be changing over time (i.e. do you expect there to be concept drift)? This could be any ...
Dennis Soemers's user avatar
  • 10.3k
3 votes

Can prior knowledge be encoded in deep neural networks?

To add to the Foivos's answer, Convolutional Neural Networks are shift-invariant. Fukushima introduced this to his Neocognitron. There is a trail to introduce scale-invariance to CNN. https://arxiv....
Yu Kobayashi's user avatar
3 votes

What are examples of techniques to prevent bias in artificial intelligence systems?

It's important to note that, ultimately, the statistical methods we currently use in ML research are just that: statistical methods. So, when they show some "bad behaviour", it's not because ...
k.c. sayz 'k.c sayz''s user avatar
2 votes

How is it that AI can become biased, and what are the proposals to mitigate this?

The key I think is teaching the algorythm by providing better data. The only thing an AI can use is the data available for itself. Figuring out whatever it can is not bias, as it's based on objective ...
Nyos's user avatar
  • 236
2 votes

What needs to be done to make a fair algorithm?

The paper Fair and Unbiased Algorithmic Decision Making: Current State and Future Challenges argues that ensuring fairness is not a trivial task and that the current statistical formalizations of ...
nbro's user avatar
  • 40.8k
1 vote

What's the purpose of layers without biases?

Bias is one of the hyperparameters in neural networks, which let you shift activation function. Disabling bias means setting bias to be zero. Even though, in many cases, bias is a big help for ...
kiarash_kiani's user avatar
1 vote
Accepted

How to add weights to one specific input feature to ensure fair training in the network?

I think your approach to tackle this as an imbalanced problem is correct. The easiest thing you could do is to add weights to the samples, during training, so that the model "pays more attention" to ...
Djib2011's user avatar
  • 3,183
1 vote

Preventing bias by not providing irrelevant data

Sometimes, the reason that this isn't an option is that you don't have that much control over what data is provided. Suppose, for example, you want a fancy AI that reads a Résumé and filters on ...
Josiah's user avatar
  • 179
1 vote

How is it that AI can become biased, and what are the proposals to mitigate this?

What are the proposals to mitigate [the AI biases]? I'll answer based on this recent survey, which focuses on Large Language Models (LLMs): Bias and Fairness in Large Language Models: A Survey: There ...
Franck Dernoncourt's user avatar
1 vote

Can prior knowledge be encoded in deep neural networks?

It kinda depends on how exactly you define knowledge, and what you believe about what the weights in a trained NN model really represent. But to answer this question in the most straightforward ...
mindcrime's user avatar
  • 3,757

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