5 accepted papers
Dense retrievers encode queries and documents and map them in an embedding space using pre-trained language models. These embeddings need to be high-dimensional to fit training signals and guarantee the retrieval effectiveness of dense retrievers. However, these high-dimensional embeddings lead to l…
Spiking neural network (SNN) is promising but the development has fallen far behind conventional deep neural networks (DNNs) because of difficult training. To resolve the training problem, we analyze the closed-form input-output response of spiking neurons and use the response expression to build ab…
In this paper we develop a new spectrum sharing scheme that uses compressive sensing to support the coexistence of the sporadic machine-to-machine (M2M) communications and the persistent conventional communications such as the 5G cellular transmissions within the same channel. The redundancy in the…
In this paper, we develop a novel scheme to reduce the amount of training data required for training deep neural networks (DNNs). We first apply a partial mutual information (PMI) technique to seek for the optimal DNN feature set. Then we use a correlation matching based active learning (CMAL) techn…
In this paper machine learning and human learning are applied jointly to optimize the training of linear regression. Human learning is exploited to label extra training data so as to resolve problems such as insufficient training and over-fitting. Considering the inevitable human errors in labeling,…