Reading Feeds

Cheatsheet of Latex Code for Reinforcement Learning Equations

rockingdingo 2022-07-18 #rl #reinforcement learning

In this blog, we will summarize the latex code of most fundamental equations of reinforcement learning (RL). This blog will cover many topics, including Bellman Equation, Markov Decision Process(MDP), Partial Observable Markov Decision Process(POMDP), DQN, A3C, etc.

Cheatsheet of Latex Code for Financial Engineering and Quantitative equations

rockingdingo 2022-07-18 #financial engineering #black-sholes

In this blog, we will summarize the latex code of most popular equations for financial engineering. We will cover important topics, including Black-Scholes formula, Value at Risk(VaR), etc.

Cheatsheet of Latex Code for Graph Neural Network(GNN) Equations

rockingdingo 2022-07-17 #graph neural network #gnn #gcn #gat #graphsage

In this blog, we will summarize the latex code of equations of Graph Neural Network(GNN) models, which are useful as quick reference for your research. For common notation, we denote G=(V,E) as the graph. V as the set of nodes with size |V|=N, and E as the set of N_e edges as |E| = N_e. A is denoted as the adjacency matrix. For each node v, we use h_v and o_v as hidde state and output vector of each node.

Cheatsheet of Latex Code for Transfer Learning Equations

rockingdingo 2022-07-17 #machine learning #transfer learning #domain adaptation #Domain-Adversarial Neural Networks

In this blog, we will summarize the latex code of most fundamental equations of transfer learning(TL). Different from multi-task learning, transfer learning models aims to achieve the best performance on target domain (minimized target domain test errors), not the performance of source domain. Typical transfer learning methods including domain adaptation(DA), feature sub-space alignment, etc. In this post, we will dicuss more details of TL equations, including many sub-areas like domain adaptation, H-divergence, Domain-Adversarial Neural Networks(DANN), which are useful as quick reference for your research.

Cheatsheet of Latex Code for Kernel Methods and Gaussian Process

rockingdingo 2022-07-11 #kernel #svm #gaussian process #gp #deep kernel learning

In this blog, we will summarize the latex code of most popular kernel methods and Gaussian Process models, including Support Vector Machine (SVM), Gaussian Process (GP) and Deep Kernel Learning(DKL).

Cheatsheet of Latex Code for Most Popular Machine Learning Equations

rockingdingo 2022-07-11 #latex #machine learning #gan #vae #kl #wasserstein

In this blog, we will summarize the latex code for most popular machine learning equations, including multiple distance measures, generative models, etc. There are various distance measurements of different data distribution, including KL-Divergence, JS-Divergence, Wasserstein Distance(Optimal Transport), Maximum Mean Discrepancy(MMD) and so on. We will provide the latex code for machine learning models in the following sections. We will also provide latex code of Generative Adversarial Networks(GAN) and Variational AutoEncoder(VAE) for generative models in the second section.

Cheatsheet of Latex Code for Multi-Task Learning Equations

rockingdingo 2022-07-11 #mtl #multi-task learning #mmoe #ple

In this blog, we will summarize the latex code of most fundamental equations of multi-task learning(MTL) and transfer learning(TL). Multi-Task Learning aims to optimize N related tasks simultaneously and achieve the overall trade-off between multiple tasks. Typical network structure include shared-bottom models, Cross-Stitch Network, Multi-Gate Mixture of Experts (MMoE), Progressive Layered Extraction (PLE), Entire Space Multi-Task Model (ESSM) models and etc. Different from multi-task learning. In the following sections, we will dicuss more details of MTL equations, which is useful for your quick reference.

Cheatsheet of Latex Code for Most Popular Causual Inference and Uplift modelling Equations

rockingdingo 2022-07-10 #causal inference #uplift modelling #auuc #qini

Cheatsheet of Latex Code for Most Popular Causual Inference and Uplift modelling Equations

Cheatsheet of Latex Code for Most Popular Recommendation and Advertisement Ranking module Equations

rockingdingo 2022-06-20 #recommendation #advertisement #ranking #sequential modelling

Ranking is a crucial part of modern commercial recommendation and advertisement system. It aims to solve the problem of accurate click-through rate(CTR) prediction. In this article, we will provides some of most popular ranking equations of commercial recommendation or ads system.

20 Tricks to Tell if Rolex Watch is Real or Fake

fashion_watch 2022-06-05 #ROLEX #FASHION #AIR-KING #GMT-MASTER-II #YACHT-MASTER-II #SUBMARINER #DAY-DATE

20 Tricks to Tell if Rolex Watch is Real or Fake

Cheatsheet of Latex Code for Most Popular Natural Language Processing Equations

rockingdingo 2022-05-03 #nlp #latex #bert

Cheatsheet of Latex Code for Most Popular Natural Language Processing Equations

Cross-Domain Recommendation in Commercial Recommendation System With application of MMD and Wasserstein distance

rockingdingo 2021-07-25 #cross domain recommendation #mmd #wasserstein

Cross-Domain Recommendation in Commercial Recommendation System With application of MMD and Wasserstein distance

Deep Candidate Generation (DeepMatch) Algorithm in recommendation

rockingdingo 2021-07-25 #deep candidate generation #deepmatch #recommendation #vector retrieval

In this post, we will talk about some real-world applications of deep candidates generation (vector-retrieval) models in the matching stage of recommendation scenario. Commercial recommendation system will recommend tens of millions of items to each user. And the recommendation process usually consists of two stages: The first stage is the candidate generation(matching) stage, a few hundred candidates are selected from the pool of all candidate items. The second stage is the ranking stage in which hundreds of items are ranked and sorted by the ranking score. Then the top rated items are displayed to users.

Tensorflow并行：多核(multicore)，多线程(multi-thread)

rockingdingo 2019-10-01 #tensorflow #并行 #多核 #多线程 #parallelism #multicore

利用tensorflow训练深度神经网络模型需要消耗很长时间，因为并行化计算就为提升运行速度提供了重要思路。Tensorflow提供了多种方法来使程序的并行运行，在使用这些方法时需要考虑的问题有：选取的计算设备是CPU还是GPU，每个CPU多少核的资源并行计算，构建图Graph时消耗资源如何分配等等问题。下面我们以Linux多核CPU的环境为例介绍几种常见方法来提升你的tensorflow程序的运行速度。

Tensorflow C++ API调用预训练模型和生产环境编译

rockingdingo 2018-11-01 #tensorflow #cpp #c++ #build #nlp #deep learning

研究如何打通tensorflow线下python脚本训练建模，线上生产环境用C++代码直接调用预先训练好的模型完成预测的工作，而不需要用自己写的Inference的函数。因为目前tensorflow提供的C++的API比较少，所以参考了几篇已有的日志，踩了不少坑一并记录下来。写了一个简单的ANN模型对Iris数据集分类的Demo。

Related Blogs