An Inclusive Learning Algorithm Framework in an increasingly Networked World of Transducers

#Machine #learning

An inclusive framework for learning algorithms will be presented discussing the “known unknowns” and speculating about “unknown unknowns” in learning algorithm development. A paradigm shift can be observed in wide-ranging application domains such as energy management, image processing, neural engineering, bioinformatics, mechatronics and the broader spectrum of design from architecture to sculpture and paintings which are empowered by rapidly-advancing technologies that can generate large quantities of “imperfect” data for analysis of processes, compounds and organisms. These applications are increasinglydemanding transparency thus the need for moving away from completely blackboxapproaches for learning. These technologies have been spurred by the improvements in processor technology (e.g. GPU), that have allowed practitioners and researchers to overcome the computational limitations of many Neural Networks that depend on fully human curated or labeled data (i.e. Supervised Learning). The following fundamental question then naturally arises: What happens when curated information or labels capture only a subset of critical classes, or the curation process itself is not fault-or error-free? Undoubtedly, the algorithm’s perceived reality will distort any subsequent analysis of these data, which may have detrimental downstream effects when new discoveries and critical decisions are made on a basis of these analyses. In such scenarios, learning algorithms that can find models –underlying structures or distinct patterns within data –without relying on labels (i.e. using Unsupervised Learning), have made great progress toward answering these sorts of questions; however, these algorithms only address part ofthe problem. Unsupervised Learning algorithms do not take into account any available and potentially reliable information or domain knowledge, which could prove useful in developing a robust model of the data. It can be advantageous to consider such information as well as any other available domain knowledge, not as ground truth but as a starting point to build a more complete picture of the problem under investigation. Some of landmark contributions in areas relevant to IEEE Computational Intelligence Society are also highlighted.

• Add Event to Calendar
  iCal
  Google Calendar

• Australian Defence Force Academy
• Northcott Drive
• Canberra, Australian Capital Territory
• Australia 2600

---

• Contact Event Host