We investigated how well deep learning algorithm can be used to navigate a partially observable (PO) grid world. And we show that VIN performs strongly for this task whilst other RL algorithms fail to generalize. The performance of VIN is compared with the ground truth that is computed by `A*` in fully observable environment. This project is supervised by Nikolay Savinov at Computer Vision and Geometry Group, ETH Zürich.
Although character-level approach has become trendy in NLP research, I couldn't find much publication that talks about it in Chinese. Perhaps it's because there are tens of thousands characters in Chinese. Here I (a non-NLP person) tried a different strategy to tackle this problem.
We replaced the Average Pooling to Max-Pooling in ANN-SNN conversion pipeline. And we reported the best SNN results in MNIST and CIFAR-10 to date.
Benchmarks have played a vital role in the advancement of visual object recognition and other fields of computer vision. We report a new benchmark dataset in which we converted established visual video benchmarks for object tracking, action recognition and object recognition into spiking neuromorphic datasets, recorded with the DVS output of a DAVIS camera.