This Job Posting Does Not Exist
Earlier this year, OpenAI released GPT-2 (Generative Pretrained Transformer), the current state-of-the-art text generation model which…
作者：Robert Sandor 来源：medium
发布时间：2019-06-23 22:46:27
Last Week in AI
Every week, my team at Invector Labs publishes a newsletter to track the most recent developments in AI research and technology. You can…
作者：Jesus Rodriguez 来源：medium
发布时间：2019-06-23 20:57:35
Adapters: A Compact and Extensible Transfer Learning Method for NLP
Adapters obtain comparable results to BERT on several NLP tasks while achieving parameter efficiency.
作者：Elvis 来源：medium
发布时间：2019-06-23 16:28:12
超越TensorFlow！未来我们需要基于图的全新计算模式
GNN崛起：未来我们需要基于图的全新计算模式，而不只是TensorFlow
作者：蔡芳芳 来源：infoq
发布时间：2019-06-23 09:00:00
打造工业级推荐系统（七）：怎么评估推荐系统的效果？
本篇文章作者来详细说明怎么评估(Evaluating)推荐系统的效果，有哪些评估手段,在推荐业务中的哪些阶段进行评估，具体的评估方法是什么。借此希望更好地帮助大家在实际业务中实施推荐系统评估模块。
作者：gongyouliu 来源：infoq
发布时间：2019-06-23 08:00:00
Handwritten Equation Solver using Convolutional Neural Network
Introduction
作者：Vipul Gupta 来源：medium
发布时间：2019-06-23 02:35:01
A Gentle Implementation of Reinforcement Learning in Pairs Trading
An Example of Structured Programming in TensorFlow
作者：Wai 来源：medium
发布时间：2019-06-23 01:38:46
A beginner’s guide to Kaggle’s Titanic problem
Since this is my first post, here’s a brief introduction of what I’ve been doing:
作者：Sumit Mukhija 来源：medium
发布时间：2019-06-23 01:34:42
Understanding Gradient Boosting Machines — using XGBoost and LightGBM parameters
A quick, practical introduction to GBMs so you can stop using them as black-boxes
作者：Nityesh Agarwal 来源：medium
发布时间：2019-06-22 22:13:17
Mixing Topology and Deep Learning with PersLay
In a former post, I presented Topological Data Analysis and its main descriptor, the so-called persistence diagram. In this post, I would…
作者：Mathieu Carrière 来源：medium
发布时间：2019-06-22 22:13:08
Types of Machine Learning in a real quick
Broadly classifying, machine learning models are of three types, supervised learning, unsupervised learning and reinforcement learning.
作者：Srishti Maurya 来源：medium
发布时间：2019-06-22 17:40:27
伯克利提出数据增强新方法，计算速度提升1000倍
来自伯克利的人工智能研究团队提出了一种基于群体的数据增强算法（PBA），这是一种能快速有效地学习最新方法来增强神经网络训练数据的算法。
作者： | 王强 来源：infoq
发布时间：2019-06-22 08:00:00
