Learning to See: You Are What You See
This work addresses bias in AI for artistic and educational audiences, but it is incremental as it builds on existing neural network techniques without introducing new methods.
The authors developed a visual instrument as part of an artwork to explore bias in artificial neural networks, enabling real-time manipulation of trained representations to question how AI and humans construct meaning.
The authors present a visual instrument developed as part of the creation of the artwork Learning to See. The artwork explores bias in artificial neural networks and provides mechanisms for the manipulation of specifically trained for real-world representations. The exploration of these representations acts as a metaphor for the process of developing a visual understanding and/or visual vocabulary of the world. These representations can be explored and manipulated in real time, and have been produced in such a way so as to reflect specific creative perspectives that call into question the relationship between how both artificial neural networks and humans may construct meaning.