Understanding and explaining deep learning models is an imperative task. Towards this, we propose a method that obtains gradient-based certainty estimates also provide visual attention maps. Particularly, solve for question answering We incorporate modern probabilistic methods further improve by using the gradients these estimates. These have two-fold benefits: a) improvement in obtaining corre...

Deep learning based salient object detection has recently achieved great success with its performance greatly outperforms any other unsupervised methods. However, annotating per-pixel saliency masks is a tedious and inefficient procedure. In this paper, we note that superior salient object detection can be obtained by iteratively mining and correcting the labeling ambiguity on saliency maps fro...

Electrical microstimulation and more recently optogenetics are widely used to map large-scale brain circuits. However, the neuronal specificity achieved with both methods is not well understood. Here we compare cell-targeted optogenetics and electrical microstimulation in the macaque monkey brain to functionally map the koniocellular lateral geniculate nucleus (LGN) projection to primary visual...

We have shown previously that cytosolic phospholipase A(2) (cPLA(2)) is responsible for endothelin-1-induced release of arachidonic acid for prostaglandin synthesis in cat iris sphincter smooth muscle (CISM) cells [Husain and Abdel-Latif (1998) Biochim. Biophys. Acta 1392, 127-144]. Here we show that p38 mitogen-activated protein (MAP) kinase, but not p42/p44 MAP kinases, plays an important rol...