Deep Learning
Self-Supervised Relational Reasoning for Representation Learning
We evaluate our method following a rigorous experimental methodology, since comparing self-supervised learning methods can be problematic (Kolesnikov et al., 2019; Musgrave et al., 2020).
Rethinking Learnable Tree Filter for Generic Feature Transform Lin Song 1 Y anwei Li
The Learnable Tree Filter presents a remarkable approach to model structure-preserving relations for semantic segmentation. Nevertheless, the intrinsic geometric constraint forces it to focus on the regions with close spatial distance, hindering the effective long-range interactions.
Counterfactual Data Augmentation using Locally Factored Dynamics
Many dynamic processes, including common scenarios in robotic control and reinforcement learning (RL), involve a set of interacting subprocesses.
Learning to Transduce with Unbounded Memory
Edward Grefenstette, Karl Moritz Hermann, Mustafa Suleyman, Phil Blunsom
Neural Information Processing Systems http://nips.cc/
Stochastic Shared Embeddings: Data-driven Regularization of Embedding Layers
Liwei Wu, Shuqing Li, Cho-Jui Hsieh, James L. Sharpnack
In deep neural nets, lower level embedding layers account for a large portion of the total number of parameters.
Dissecting Neural ODEs Stefano Massaroli The University of Tokyo, DiffEqML
Continuous deep learning architectures have recently re-emerged as Neural Ordinary Differential Equations (Neural ODEs).
A Recurrent Latent Variable Model for Sequential Data
Junyoung Chung, Kyle Kastner, Laurent Dinh, Kratarth Goel, Aaron C. Courville, Yoshua Bengio
Neural Information Processing Systems http://nips.cc/
mixup-uq.pdf
Additionally, we find that merely mixing features does not result in the same calibration benefit and that the label smoothing in mixup training plays a significant role in improving calibration.
