Boltzmann machines are often used as building blocks in greedy learning of deep networks. However, training even a simplified model, known as restricted Boltzmann machine, can be extremely laborious: Traditional learning algorithms often converge only with the right choice of the learning rate scheduling and the scale of the initial weights. They are also sensitive to specific data representati...

Students are naturally curious and inquisitive with powerful intrinsic motives to probe, learn, and understand their world. Accordingly, class activities must capitalize on this inherently energetic and curious nature so that learning becomes a lifelong activity where students take initiative for learning, are skilled in learning, and want to learn new things. This report describes a student-ce...

Lujan HL, DiCarlo SE. The flipped exam: creating an environment in which students discover for themselves the concepts and principles we want them to learn. Adv Physiol Educ 38: 339–342, 2014; doi:10.1152/advan.00081.2014.—Students are naturally curious and inquisitive with powerful intrinsic motives to probe, learn, and understand their world. Accordingly, class activities must capitalize on t...

This paper presents a new algorithm, Magnitude Sensitive Competitive Learning (MSCL), which has the ability of distributing the unit weights following any magnitude calculated from the unit parameters or the input data inside the Voronoi region of the unit. This controlled behavior permits to surpass other standard Competitive Learning algorithms that only tend to concentrate neurons accordingl...