I
Irwan Bello
Researcher at Google
Publications - 20
Citations - 3541
Irwan Bello is an academic researcher from Google. The author has contributed to research in topics: Artificial neural network & Deep learning. The author has an hindex of 12, co-authored 18 publications receiving 2144 citations.
Papers
More filters
Proceedings Article
Neural Combinatorial Optimization with Reinforcement Learning
TL;DR: A framework to tackle combinatorial optimization problems using neural networks and reinforcement learning, and Neural Combinatorial Optimization achieves close to optimal results on 2D Euclidean graphs with up to 100 nodes.
Proceedings ArticleDOI
Attention Augmented Convolutional Networks
TL;DR: Li et al. as mentioned in this paper concatenated convolutional feature maps with a set of feature maps produced via a novel relative self-attention mechanism, which attends jointly to both features and spatial locations while preserving translation equivariance.
Posted Content
Attention Augmented Convolutional Networks
TL;DR: It is found that Attention Augmentation leads to consistent improvements in image classification on ImageNet and object detection on COCO across many different models and scales, including ResNets and a state-of-the art mobile constrained network, while keeping the number of parameters similar.
Proceedings Article
Stand-Alone Self-Attention in Vision Models
TL;DR: The results establish that stand-alone self-attention is an important addition to the vision practitioner's toolbox and is especially impactful when used in later layers.
Posted Content
Neural Combinatorial Optimization with Reinforcement Learning
TL;DR: In this paper, the traveling salesman problem (TSP) is solved using reinforcement learning and a recurrent network that predicts a distribution over different city permutations using negative tour length as the reward signal.