Search Results for author:
Found 12 papers, 6 papers with code
Evolutionary Optimization of Model Merging Recipes
Surprisingly, our Japanese Math LLM achieved state-of-the-art performance on a variety of established Japanese LLM benchmarks, even surpassing models with significantly more parameters, despite not being explicitly trained for such tasks.
Team PFDet's Methods for Open Images Challenge 2019
Using this method, the team PFDet achieved 3rd and 4th place in the instance segmentation and the object detection track, respectively.
Chainer: A Deep Learning Framework for Accelerating the Research Cycle
Software frameworks for neural networks play a key role in the development and application of deep learning methods.
Optuna: A Next-generation Hyperparameter Optimization Framework
We will present the design-techniques that became necessary in the development of the software that meets the above criteria, and demonstrate the power of our new design through experimental results and real world applications.
A Graph Theoretic Framework of Recomputation Algorithms for Memory-Efficient Backpropagation
Recomputation algorithms collectively refer to a family of methods that aims to reduce the memory consumption of the backpropagation by selectively discarding the intermediate results of the forward propagation and recomputing the discarded results as needed.
Sampling Techniques for Large-Scale Object Detection from Sparsely Annotated Objects
However, large datasets like Open Images Dataset v4 (OID) are sparsely annotated, and some measure must be taken in order to ensure the training of a reliable detector.
PFDet: 2nd Place Solution to Open Images Challenge 2018 Object Detection Track
We present a large-scale object detection system by team PFDet.
Adversarial Attacks and Defences Competition
To accelerate research on adversarial examples and robustness of machine learning classifiers, Google Brain organized a NIPS 2017 competition that encouraged researchers to develop new methods to generate adversarial examples as well as to develop new ways to defend against them.
Variance-based Gradient Compression for Efficient Distributed Deep Learning
We also analyze the efficiency using computation and communication cost models and provide the evidence that this method enables distributed deep learning for many scenarios with commodity environments.
ShakeDrop Regularization for Deep Residual Learning
In this paper, to relieve the overfitting effect of ResNet and its improvements (i. e., Wide ResNet, PyramidNet, and ResNeXt), we propose a new regularization method called ShakeDrop regularization.
Extremely Large Minibatch SGD: Training ResNet-50 on ImageNet in 15 Minutes
We demonstrate that training ResNet-50 on ImageNet for 90 epochs can be achieved in 15 minutes with 1024 Tesla P100 GPUs.
ChainerMN: Scalable Distributed Deep Learning Framework
One of the keys for deep learning to have made a breakthrough in various fields was to utilize high computing powers centering around GPUs.
