Xu Cui
•
567 Stories by Xu Cui
In this project, I built a neural network for machine translation (English -> French). I built and trained a sequence to sequence model on a dataset of English and French sentences that can translate new sentences from English to French. The mode
The following email was sent from Stork to me. Stork is an easy-to-use app to alert me of new scientific publications and NIH grants based on my own keywords. Below are a few grants awarded in the NIRS field. Dear Xu, Stork has brought you 15 new pub
It requires a lot of resources, especially GPU and GPU memory, to train a deep-learning model efficiently. Here I test the time it took to train a model in 3 computers/servers. 1. My own laptop. CPU: Intel Core i7-7920HQ (Quad Core 3.10GHz, 4.10GHz T
Brain Dynamics Lab (bdl.stanford.edu) is a computational neuropsychiatry lab dedicated to developing computational methods for a better understanding of individual differences in brain functioning in healthy and patient populations. Current projects
PubMed是生物和医学领域必不可少的搜索引擎，每天百万名医生、教授、学生及其他科研人员等都会通过PubMed搜索自己感兴趣的科学文献、病例、综述、最新进展等。 可惜，PubMed是全英文的！！！ 为
In this class project, I generated my own Simpsons TV scripts using RNNs trained by the Simpsons dataset of scripts from 27 seasons. The Neural Network generated a new TV script for a scene at Moe’s Tavern. This is the script generated by the n
The speed difference of CPU and GPU can be significant in deep learning. But how much? Let’s do a test. The computer: The computer I use is a Amazon AWS instance g2.2xlarge (https://aws.amazon.com/ec2/instance-types/). The cost is $0.65/hour, o
Some labs have been using our script readHitachiData.m to load NIRS data from Hitachi ETG machines. We recently found that some output MES data contains abnormal timestamp. For example, the timestamp should be like 16:49:25.406 But for some rows (alt
In this class project, I built a network to classify images in the CIFAR-10 dataset. This dataset is freely available. The dataset contains 60K color images (32×32 pixel) in 10 classes, with 6K images per class. Here are the classes in the datas