We propose to reinterpret a standard discriminative classifier of p(y|x) as an energy based model for the joint distribution p(x, y). In this setting, the standard class probabilities can be easily computed as well as unnormalized values of p(x) and p(x|y). Within this framework, standard discriminative architectures may be used and the model can also be trained on unlabeled data. We demonstrate that energy based training of the joint distribution improves calibration, robustness, and out-of-distribution detection while also enabling our models to generate samples rivaling the quality of recent GAN approaches. We improve upon recently proposed techniques for scaling up the training of energy based models and present an approach which adds little overhead compared to standard classification training. Our approach is the first to achieve performance rivaling the state-of-the-art in both generative and discriminative learning within one hybrid model.
Speaker embedding models that utilize neural networks to map utterances to a space where distances reflect similarity between speakers have driven recent progress in the speaker recognition task. However, there is still a significant performance gap between recognizing speakers in the training set and unseen speakers. The latter case corresponds to the fewshot learning task, where a trained model is evaluated on unseen classes. Here, we optimize a speaker embedding model with prototypical network loss (PNL), a state-of-the-art approach for the few-shot image classification task. The resulting embedding model outperforms the state-of-the-art triplet loss based models in both speaker verification and identification tasks, for both seen and unseen speakers.
The stress-upregulated catecholamines-activated β1- and β2-adrenergic receptors (β1/2-ARs) have been shown to accelerate the progression of cancers such as colorectal cancer (CRC). We investigated the underlying mechanism of the inhibition of β1/2-ARs signaling for the treatment of CRC and elucidated the significance of β2-AR expression in CRC in vitro and in clinical samples. The impacts of β1/2-AR antagonists in CRC in vitro and CRC-xenograft in vivo were examined. We found that repression of β2-AR but not β1-AR signaling selectively suppressed cell viability, induced G1-phase cell cycle arrest, caused both intrinsic and extrinsic pathways-mediated apoptosis of specific CRC cells and inhibited CRC-xenograft growth in vivo. Moreover, the expression of β2-AR was not consistent with the progression of CRC in vitro or in clinical samples. Our data evidence that the expression profiles, signaling, and blockage of β2-AR have a unique pattern in CRC comparing to other cancers. β2-AR antagonism selectively suppresses the growth of CRC accompanying active β2-AR signaling, which potentially carries wild-type KRAS, in vitro and in vivo via the inhibition of β2-AR transactivated EFGR-Akt/ERK1/2 signaling pathway. Thus, β2-AR blockage might be a potential therapeutic strategy for combating the progressions of β2-AR-dependent CRC.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.