vortimaya.blogg.se - Block world problem in ai

The inclusion of explainable AI techniques by design in the AI/ML models offers significant benefits to those involved:

Controlling the model’s behaviours to avoid discrimination and reduce societal bias.

Debugging odd behaviours from the model.

Explaining why an individual entry receives a concrete prediction or classification, improving human readability.

Presenting the model to a non-technical audience with interests in the treated use case.

This understanding of a model’s behaviour is very important for the following main reasons: Sometimes there is the dilemma of having to accept a particular model (a LSTM Neural Network for example) that works much better than another (a simple Logistic Regression), although it is more difficult to understand and explain.Īnother major problem is that if there is a bias in the data used to train AI/ML algorithms, then that bias will be present in the decisions that the algorithms make, and this is clearly unacceptable.Įxplainable AI refers generally to methods and techniques that enable an understanding of why an AI/ML model is giving specific results. Powerful AI/ML (Machine Learning) models, in particular Deep Neural Networks, tend to be very hard to explain (“Black Box problem”). But explainability is extremely crucial in systems that are responsible for decisions and automated actions.

For example in 2019 Apple co-founder Steve Wozniak accused Apple Card of gender discrimination through its algorithm, denouncing the fact that the card gave him a credit limit ten times higher than his wife's, despite the fact that the couple shared all their assets.Īrtificial Intelligence provides great benefits for organisations, boosting their efficiency and enabling new ways of working. In fact, several notorious cases have occurred in the industry recently. This situation is unfortunately already being played out in real life. However, the bank manager tells you that unfortunately it is the result dictated by the bank’s new Artificial Intelligence algorithm, and s/he cannot explain to you the reason for the rejection. You have been a good customer of the bank for the last fifteen years and therefore you don’t understand the decision and you ask for an explanation. Imagine that you go to your usual bank to request a loan to carry out works in your home, and after a quick analysis on his/her computer, the bank manager informs you that it cannot be approved. Mobile Competence Centre & Innovation, and Minh Le, Head of Connected Vehicle & Emerging IoT Offerings

Contributors: Jose Maria Lopez, Head of Bus.