Can we open the black box of AI?

  title={Can we open the black box of AI?},
  author={Davide Castelvecchi},

Transparent but Accurate Evolutionary Regression Combining New Linguistic Fuzzy Grammar and a Novel Interpretable Linear Extension

This work proposes a new extension of the fuzzy linguistic grammar and a mainly novel interpretable linear extension for regression problems, together with an enhanced new linguistic tree-based evolutionary multiobjective learning approach, which allows the general behavior of the data covered, as well as their specific variability, to be expressed as a single rule.

Cognitive Automation und die Zukunft der Arbeit: Eine integrierte Konzeptualisierung und Einblicke aus der Unternehmensrealität

Vor dem Hintergrund der Künstlichen Intelligenz, durch Maschinelles Lernen fazilitiert, bewegt sich Cognitive Automation (CA) über deterministische Geschäftsprozessautomatisierung, wie z.B. Robotic


This work creates a new semi-supervised clustering method, that can be extended to a pseudo-labelling deep learning scheme, and furthermore have the capability to utilize an octree mesh for larger datasets or faster clusterings.

Constrained Interval Type-2 Fuzzy Classification Systems for Explainable AI (XAI)

It will be shown how constrained intervaltype-2 (CIT2) fuzzy sets represent a valid alternative to conventional interval type-2 sets in order to address the growing need for intelligent systems that can produce explanations for the decisions they make.

Deep learning for human engineered systems: Weak supervision, interpretability and knowledge embedding

A chronology of key events and events leading to the creation of the modern-day Republic of Ireland is described.

Behavioural analysis of single-cell aneural ciliate, Stentor roeselii, using machine learning approaches

The results showed that an artificial neural network with multiple ‘computational’ neurons is inefficient at modelling the single-celled ciliate’s avoidant reactions, and highlighted the complexity of behaviours in aneural organisms.

Evolutionary Fuzzy Systems for Explainable Artificial Intelligence: Why, When, What for, and Where to?

It will be pointed out why evolutionary fuzzy systems are important from an explainable point of view, when they began, what they are used for, and where the attention of researchers should be directed to in the near future in this area.

The Evaluation of the Black Box Problem for AI-Based Recommendations: An Interview-Based Study

A model based on the theory of planned behavior explaining the relation between the user’s perception of the black box problem and the attitude toward AI-based recommendations distinguishing between a mandatory and voluntary use context is developed.

Artificial Intelligence-Based Analytics for Diagnosis of Small Bowel Enteropathies andBlack Box Feature Detection

An AI-based image analysis platform demonstrated high classification accuracy for small bowel enteropathies which was capable of identifying biologically relevant microscopic features, emulating human pathologist decision making process, performing in the case of suboptimal computational environment, and being modified for improving disease classification accuracy.

Behavioural analysis of single-cell aneural ciliate, Stentor roeseli, using machine learning approaches

Whether models inferred from machine learning approaches, including decision tree, random forest and feed-forward artificial neural networks could infer and predict the behaviour of S. roeseli was investigated and showed that an artificial neural network with multiple ‘computational’ neurons is inefficient at modelling the single-celled ciliate's avoidance reactions.



Probabilistic machine learning and artificial intelligence

This Review provides an introduction to this framework, and discusses some of the state-of-the-art advances in the field, namely, probabilistic programming, Bayesian optimization, data compression and automatic model discovery.

ImageNet classification with deep convolutional neural networks

A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.

Distilling Free-Form Natural Laws from Experimental Data

This work proposes a principle for the identification of nontriviality, and demonstrated this approach by automatically searching motion-tracking data captured from various physical systems, ranging from simple harmonic oscillators to chaotic double-pendula, and discovered Hamiltonians, Lagrangians, and other laws of geometric and momentum conservation.