开源算法与数据库
论文阅读
机器学习干货
产业现状
编程练习
杂谈
2016 年 9 月 7 日前
微信收藏
2016 年 8 月 28 日前
微博收藏
How Image Degradations Affect Deep CNN-based Face Recognition? 答案是影响很大,文章有一定的启发意义。
Formulating The ReLU 从 ReL, Sigmoid 讲到 ReLU。
NN++: A small and easy to use neural net implementation for C++
Language necessarily contains human biases, and so will machines trained on language corpora
SAND GLYPHS: 字体生成. GitHub: sand-glyphs
Torch implementation for the paper “Artistic style transfer for videos”
Survey of resampling techniques for improving classification performance in unbalanced datasets
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
Convolutional network training using Torch | 从 AlexNet 到 ResNet 各种 models
Understanding Convergence Concepts: A Visual-Minded and
Graphical Simulation-Based Approach R PackageSemantic Image Inpainting with Perceptual and Contextual Losses
Deep Learning Part 1: Comparison of Symbolic Deep Learning Frameworks
Keras code and weights files for popular deep learning models.
Bridging the Gap between Stochastic Gradient MCMC and Stochastic Optimization Github
欺骗人脸识别系统:Spoofing 2D Face Detection: Machines See People Who Aren’t There
The best explanation of Convolutional Neural Networks on the Internet!
微信收藏
Deep Learning Part 2: Transfer Learning and Fine-tuning Deep Convolutional Neural Networks
最前沿:神经网络训练方法大革新,反向传播训练不再唯一 反向传播?人脑真的是这样做的吗?还能怎么做?预测梯度。用什么预测?另一组神经网络。戳论文:Decoupled Neural Interfaces using Synthetic Gradients
6.
2016 年 8 月 20 日前
微信收藏
微博收藏
fancy-cnn - Sequential convolutional architectures for text classification
How to Develop Your First XGBoost Model in Python with scikit-learn
An Empirical Evaluation of doc2vec with Practical Insights into Document Embedding Generation
“Why Should I Trust You?”: Explaining the Predictions of Any Classifier