Deep Learning
Large-batch Optimization for Dense Visual Predictions: Training Faster R-CNN in 4.2 Minutes
Training a large-scale deep neural network in a large-scale dataset is challenging and time-consuming. The recent breakthrough of large-batch optimization is a promising way to tackle this challenge.
Emergent Communication under Varying Group Sizes and Connectivities
Figure 1: Left: A scenario in which two agents speak different languages to describe the same object.
PLLay: Efficient Topological Layer based on Persistence Landscapes
With its strong generalizability, deep learning has been pervasively applied in machine learning.
Supplementary Material for: Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains A Relation to other RNNs
In Sec. 3 we set out to create an RNN LSTMs use two gates, i.e. a forget and an input gate, with the sigmoid activation function Nonetheless, it is not straight forward to apply our approach, outlined in Sec. 3, to GRUs and LSTMs. Our loss (see Eq. 5) punishes non-zero gate activation. Thus, their gating function would need to be modified or replaced, e.g. by our ReTanh gate GateL0RD attempts to overcome the outlined downsides of using LSTMs and GRUs with our proposed latent state regularization. B.2 - B.5 provide further details specific to each Billiard Ball scheduled sampling (Sec. The best learning rates for all experiments are listed in Table 1.