Neural Topic Modeling for Document Networks with Adjacent-Encoder
Text documents are usually linked to one another. For example, academic papers cite other papers, web pages link to other pages, etc. Most of...
Recent Posts
Why maximum likelihood-based training may lead to the generation of unrealistic samples
Generative models specify procedures allowing us to produce data samples, e.g., images, texts, user preferences, etc. These models are central to unsupervised learning, and...
Call for Interns 2020
Preferred.AI is calling for internship applications from current students of SMU to work with us during the summer (May to July 2020) on a...
The Zen of Comparisons
During the teaching appointment at Montana State University, Robert M. Pirsig, the author of “Zen and the Art of Motorcycle Maintenance“, conducted a following...
Gaining Perspective
On 11 September 2019, Andrew successfully passed the defense of his PhD dissertation, entitled “Preference Learning and Similarity Learning Perspectives on Personalized Recommendation”. He...
IJCAI 2019 in Macau, China
In August 2019, Andrew attended the 28th International Joint Conference on Artificial Intelligence (IJCAI-2019). He shares his learning and experience in this blog post....
TechFest 2019
Preferred.AI held a TechFest on Friday 23 August 2019, 3.30pm – 6.30pm to share the recent projects that we’re actively pursuing. Captivating talks based...
Context Matters: Why Aren’t You Leveraging Items’ Context to Boost Your Recommender Model?
Data sparsity is one of the biggest challenges in recommender systems. A promising solution to alleviate this problem is to rely on auxiliary sources...
The Web Conference 2019 in San Francisco
In May 2019, Hady traveled to San Francisco for the Web Conference 2019 (previously the conference series was known as World Wide Web or...
Introduction to CSVPL
Here in Preferred.AI, much of our work involves processing and manipulating data. We regularly find ourselves wanting to explore a given dataset quickly and...
