Jianmin Wang

Transductive Zero-Shot Recognition via Shared Model Space Learning

2016 · Proceedings of the AAAI Conference on Artificial Intelligence

Zero-shot Recognition (ZSR) is to learn recognition models for novel classes without labeled data. It is a challenging task and has drawn considerable attention in recent years. The basic idea is to transfer knowledge from …

Learning Stages: Phenomenon, Root Cause, Mechanism Hypothesis, and Implications.

2019 · arXiv (Cornell University)

Learning rate decay (lrDecay) is a \emph{de facto} technique for training modern neural networks. It starts with a large learning rate and then decays it multiple times. It is empirically observed to help both optimization …

Requirements Engineering for Machine Learning: A Review and Reflection

2022 · arXiv (Cornell University)

Today, many industrial processes are undergoing digital transformation, which often requires the integration of well-understood domain models and state-of-the-art machine learning technology in business processes. However, requirements elicitation and design decision making about when, where …