The Self-Taught Translator

Hindustani Self-Taught

ALADIN: The self-taught vocal interface

We describe a demonstration of a novel vocal user interface (VUI), ALADIN, which is trained through usage, by demonstrating spoken commands with manual controls. It works by mining the vocal commands to find recurrent acoustic patterns corresponding to words or phrases that constitute elements of the user’s commands. The demonstration consists of the VUI controlling a 3D environment with home a...

Self-Taught Support Vector Machine

In this paper, a new approach for classification of target task using limited labeled target data as well as enormous unlabeled source data is proposed which is called self-taught learning. The target and source data can be drawn from different distributions. In the previous approaches, covariate shift assumption is considered where the marginal distributions ) (x p change over domains and the ...

Robust and Discriminative Self-Taught Learning

The lack of training data is a common challenge in many machine learning problems, which is often tackled by semi-supervised learning methods or transfer learning methods. The former requires unlabeled images from the same distribution as the labeled ones and the latter leverages labeled images from related homogenous tasks. However, these restrictions often cannot be satisfied. To address this...

Philomaths, Herschel, and the myth of the self-taught man.

The role of technicians and background characters in the historical practice of science is slowly gaining recognition. This paper looks at the collective effort involved in learning science, using as my case study the eighteenth-century musician turned astronomer, William Herschel. Lacking a university education, Herschel, like many contemporaries, presented himself as self-taught, thereby hidi...