Adam Coates
Demystifying Unsupervised Feature Learning
Machine learning is a key component of state-of-the-art systems in many application domains. Applied to many kinds of raw data, however, most learning algorithms are unable to make good predictions. In order to succeed, most learning algorithms are applied instead to “features” that represent higher-level concepts extracted from the raw data. These features, developed by expert practitioners in each field, encode important prior knowledge about the task that the learning algorithm would be unable to discover on its own from (often limited) labeled training examples. Unfortunately, engineering good feature representations for new applications is extremely difficult. For the most challenging applications in AI, like computer vision, the search for good features and higher-level image representations is vast and ongoing.
For those looking for more and deeper information on the topic, here are some additional links an resources to look at:
- Lots of publications and demo code from the speaker
- Autonomous Helicopter project at Stanford University
Join us any time and get to be a better coder!