Learning without Concentration

Learning Theory: Concentration Inequalities

Sequential Learning without Feedback

In many security and healthcare systems a sequence of features/sensors/tests are used for detection and diagnosis. Each test outputs a prediction of the latent state, and carries with it inherent costs. Our objective is to learn strategies for selecting tests to optimize accuracy & costs. Unfortunately it is often impossible to acquire-in-situ ground truth annotations and we are left with the p...

Learning without Training

Achieving high-level skills is generally considered to require intense training, which is thought to optimally engage neuronal plasticity mechanisms. Recent work, however, suggests that intensive training may not be necessary for skill learning. Skills can be effectively acquired by a complementary approach in which the learning occurs in response to mere exposure to repetitive sensory stimulat...

Reinforcement Learning Without Rewards

Machine learning can be broadly defined as the study and design of algorithms that improve with experience. Reinforcement learning is a variety of machine learning that makes minimal assumptions about the information available for learning, and, in a sense, defines the problem of learning in the broadest possible terms. Reinforcement learning algorithms are usually applied to “interactive” prob...

Perceptual learning without signal

Perceptual learning is characterized by an improvement in a perceptual task following practice. Several studies have demonstrated that top-down processes, such as attention and task-related expectations, can be necessary components of perceptual learning [Ahissar & Hochstein, 1993, 2000, 2002; Fahle & Morgan, 1996; Seitz, Lefebvre, Watanabe, & Jolicoeur, 2005; Seitz, Nanez, Holloway, Koyama, & ...