Zum Hauptinhalt springen

Artificial Intelligence - An Overview

Artificial intelligence (AI) can be described as the intelligence of machines that works similar to human intelligence. So far, individual algorithms can solve specific tasks at human level and beyond. There is, however, no artificial general intelligence (AGI), yet.

Machine Learning​

Machine learning (ML) refers to the learning process of an algorithm, which is iteratively adjusting its parameters to solve the given task. It can be divided into the following subfields:

  • Supervised machine learning: Supervised machine learning works with labeled data by learning through input-output pairs.
  • Unsupervised machine learning:
    The difference of unsupervised to supervised machine learning are the missing labels of the data. Unsupervised learning uses patterns in the data to associate similar data points with one another.
  • Semi-supervised learning: Semi-supervised learning is the connection of unsupervised with supervised machine learning. By using for example a (unsupervised) clustering algorithm before using a supervised learning technique, the data can be pre-structured beforehand, which can be useful.
  • Reinforcement learning:
    In reinforcement learning, an agent interacts with an environment and gets rewards by following given rules or execute desired actions.

Neural networks​

Neural networks are a subcategory of ML, which is based on the idea of neurons in a human brain. A neural network consists of connected nodes, which are configured in an input layer, hidden layers and an output layer. In each layer an activation function is applied and after that, the values are weighted and propagated to the next layer. In the learning process the weights are adjusted.

Deep learning​

Deep learning models consist of neural networks with a higher amount of layers. This opens up the possibility to work with more complex data and also achieving higher accuracies.

References​

  • Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT press.

  • Jiang, Y., Li, X., Luo, H., Yin, S., & Kaynak, O. (2022). Quo vadis artificial intelligence?. Discover Artificial Intelligence, 2(1), 4.

  • LeCun, Y., Bengio, Y. & Hinton, G. (2015). Deep learning. Nature 521, 436–444. https://doi.org/10.1038/nature14539

  • Ray, S. (2019). A quick review of machine learning algorithms. In 2019 International conference on machine learning, big data, cloud and parallel computing (COMITCon), 35-39. https://doi.org/10.1109/COMITCon.2019.8862451

  • Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction. MIT press.

  • Usama, M., Qadir, J., Raza, A., Arif, H., Yau, K., Elkhatib, Y., Hussain, A., & Al-Fuqaha, A. (2019). Unsupervised machine learning for networking: Techniques, applications and research challenges. In IEEE Access, vol. 7, pp. 65579-65615. https://doi.org/10.1109/ACCESS.2019.2916648