|
You are here |
kpzhang93.github.io | ||
| | | | |
sander.ai
|
|
| | | | | Slides for my talk at the Deep Learning London meetup | |
| | | | |
ojs.aaai.org
|
|
| | | | | [AI summary] The article introduces ST-ResNet, a deep learning model designed to predict city-wide crowd flows by analyzing spatio-temporal data and external factors like weather across regions in Beijing and New York City. | |
| | | | |
ssc.io
|
|
| | | | | Retrieval augmentation enables large language models to take advantage of external knowledge, for example on tasks like question answering and data imputation. However, the performance of such retrieval-augmented models is limited by the data quality of their underlying retrieval corpus. In this paper, we propose an algorithm based on multilinear extension for evaluating the data importance of retrieved data points. There are exponentially many terms in the multilinear extension, and one key contribution of this paper is a polynomial time algorithm that computes exactly, given a retrieval-augmented model with an additive utility function and a validation set, the data importance of data points in the retrieval corpus using the multilinear extension of the mo... | |
| | | | |
teddykoker.com
|
|
| | | In this post we will be using a method known as transfer learning in order to detect metastatic cancer in patches of images from digital pathology scans. | ||