12

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 and training data is publicly available. Also it changes frequently as they work to improve the service. As such, it is hard to tell what exactly is leading it ...


5

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 "value" (whatever that is, class/regression) of the object we are looking is rotational/translational invariant (our prior knowledge), then we augment the data ...


4

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 connections? If so, how? If not, why has this not been considered before? Yes. The AI/ model still can learn those prejudiced connections. Consider that you have a ...


4

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 was followed all over the web by ads for aids for the infirm elderly. Users who recognize that Google uses their searches to build their profile can alter their ...


4

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 vectors likes $(a, b, a^2 + b^2)$. As another example, suppose date time is important in your data, but not encoded in the input vector. We can add this to the ...


4

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: regardless of the algorithm you use, you cant get learning "for free"(i.e by just looking at the training examples). The reason for this is that the only thing ...


4

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 ACM: [Algorithms] often inadvertently pick up the human biases that are incorporated when the algorithm is programmed, or when humans interact with that ...


3

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.org/abs/1411.6369 Also, CNN uses structural characteristic for the prior knowledge. And neural networks are locally smooth. It is not perfect, but neural ...


3

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 kind of change. Simply changes in how frequent certain inputs are, changes in how frequent positives/negatives are, or even changes in relations between inputs ...


3

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 of problems with the statistical methods, but with the data we give it. But if the data we give it are as "genuine and unfiltered" as it gets, then it probably shows ...


2

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 facts. If it knows 98% of Nguyens are interested in X, knowing nothing else about you personally, showing you X might be good. If you consistently click on ...


2

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 fairness lead to a long list of criteria that are each flawed (or even harmful) in different contexts, that is, there are trade-offs between the proposed ...


1

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 successful learning, in some cases, you may want to add an extra constraint to your neural network in finding the objective function. For example, in the paper below, ...


1

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 the under-represented class. There are also a couple of other ways for this to be done: oversampling and undersampling, but initially, I'd focus on adding ...


1

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 suitability for a job. There isn't a particularly rigid formula about what people put in their Résumé, which makes it difficult to exclude things you'd rather not ...


1

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 possible way (hopefully without sounding glib), then yes, a NN can be pre-trained, and then you can take that model and apply additional training to it, so in a sense,...


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