The combination of magic angle spinning (MAS) with the high-resolution 1 H NOESY NMR experiment is an established method for measuring through-space 1 H… 1 H dipolar couplings in biological membranes. The segmental motion of the lipid acyl chains along with the overall rotational diffusion of the lipids provides sufficient motion to average the 1 H dipolar interaction to within the range where MAS can be effective. One drawback of the approach is the relatively long NOESY mixing times needed for relaxation processes to generate significant crosspeak intensity. In order to drive magnetization transfer more rapidly, we use solid-state radiofrequency driven dipolar recoupling (RFDR) pulses during the mixing time. We compare the 1 H MAS NOESY experiment with a 1 H MAS RFDR experiment on dimyristoylphosphocholine, a bilayer forming lipid, and show that the 1 H MAS RFDR experiment provides considerably faster magnetization exchange than the standard 1 H MAS NOESY experiment. We apply the method to model compounds containing basic and aromatic amino acids bound to membrane bilayers to illustrate the ability to locate the position of aromatic groups that have penetrated to below the level of the lipid headgroups.

No abstract

We applied pre-defined kernels also known as filters or masks developed for image processing to convolution neural network. Instead of letting neural networks find its own kernels, we used 41 different general-purpose kernels of blurring, edge detecting, sharpening, discrete cosine transformation, etc. for the first layer of the convolution neural networks. This architecture, thus named as general filter convolutional neural network (GFNN), can reduce training time by 30% with a better accuracy compared to the regular convolutional neural network (CNN). GFNN also can be trained to achieve 90% accuracy with only 500 samples. Furthermore, even though these kernels are not specialized for the MNIST dataset, we achieved 99.56% accuracy without ensemble nor any other special algorithms.

No abstract

There are various pixel-based interpretation methods such as saliency map, gradient×input, DeepLIFT, integrated-gradient-n, etc. However, it is difficult to compare their performance as it involves human cognitive processes. We propose a metric that can quantify the distance from the importance scores of the interpretation methods to human intuition. We create a new dataset by adding a simple and small image, named as a stamp, to the original images. The importance scores for the deep neural networks to classify the stamped and regular images are calculated. Ideally, the pixel-based interpretation has to successfully select the stamps. Previous methods to compare different interpretation methods are useful only when the scale of the importance scores is the same. Whereas, we standardize the importance scores and define the measure to ideal scores. Our proposed method can quantitatively measure how the interpretation methods are close to human intuition.