Latest Articles

324 articles · Fresh posts aggregated from independent blogs across the directory.

LLil'LogLil'Log·Oct 13, 2018

Flow-based Deep Generative Models

So far, I’ve written about two types of generative models, GAN and VAE. Neither of them explicitly learns the probability density function of real data, $p(\mathbf{x})$ (where $\mathbf{x} \in \mathcal{D}$) — because it is really hard! Taking the generative mo…

lilianweng.github.ioRead article
LLil'LogLil'Log·Aug 12, 2018

From Autoencoder to Beta-VAE

[Updated on 2019-07-18: add a section on VQ-VAE & VQ-VAE-2.] [Updated on 2019-07-26: add a section on TD-VAE.] Autocoder is invented to reconstruct high-dimensional data using a neural network model with a narrow bottleneck layer in the middle (oops, this…

lilianweng.github.ioRead article
LLil'LogLil'Log·Jun 24, 2018

Attention? Attention!

[Updated on 2018-10-28: Add Pointer Network and the link to my implementation of Transformer.] [Updated on 2018-11-06: Add a link to the implementation of Transformer model.] [Updated on 2018-11-18: Add Neural Turing Machines.] [Updated on 2019-07-18: Correct…

lilianweng.github.ioRead article
LLil'LogLil'Log·Apr 8, 2018

Policy Gradient Algorithms

[Updated on 2018-06-30: add two new policy gradient methods, SAC and D4PG.] [Updated on 2018-09-30: add a new policy gradient method, TD3.] [Updated on 2019-02-09: add SAC with automatically adjusted temperature]. [Updated on 2019-06-26: Thanks to Chanseok, w…

lilianweng.github.ioRead article
LLil'LogLil'Log·Jan 23, 2018

The Multi-Armed Bandit Problem and Its Solutions

The algorithms are implemented for Bernoulli bandit in lilianweng/multi-armed-bandit. Exploitation vs Exploration The exploration vs exploitation dilemma exists in many aspects of our life. Say, your favorite restaurant is right around the corner. If you go t…

lilianweng.github.ioRead article
LLil'LogLil'Log·Dec 31, 2017

Object Detection for Dummies Part 3: R-CNN Family

[Updated on 2018-12-20: Remove YOLO here. Part 4 will cover multiple fast object detection algorithms, including YOLO.] [Updated on 2018-12-27: Add bbox regression and tricks sections for R-CNN.] In the series of “Object Detection for Dummies”, we started wit…

lilianweng.github.ioRead article
LLil'LogLil'Log·Oct 15, 2017

Learning Word Embedding

Human vocabulary comes in free text. In order to make a machine learning model understand and process the natural language, we need to transform the free-text words into numeric values. One of the simplest transformation approaches is to do a one-hot encoding…

lilianweng.github.ioRead article
LLil'LogLil'Log·Sep 28, 2017

Anatomize Deep Learning with Information Theory

Professor Naftali Tishby passed away in 2021. Hope the post can introduce his cool idea of information bottleneck to more people. Recently I watched the talk “Information Theory in Deep Learning” by Prof Naftali Tishby and found it very interesting. He presen…

lilianweng.github.ioRead article
LLil'LogLil'Log·Aug 20, 2017

From GAN to WGAN

[Updated on 2018-09-30: thanks to Yoonju, we have this post translated in Korean!] [Updated on 2019-04-18: this post is also available on arXiv.] Generative adversarial network (GAN) has shown great results in many generative tasks to replicate the real-world…

lilianweng.github.ioRead article
LLil'LogLil'Log·Jul 22, 2017

Predict Stock Prices Using RNN: Part 2

In the Part 2 tutorial, I would like to continue the topic on stock price prediction and to endow the recurrent neural network that I have built in Part 1 with the capability of responding to multiple stocks. In order to distinguish the patterns associated wi…

lilianweng.github.ioRead article
HHello World: Re-ActHello World: Re-Act·Apr 11, 2014

微软创投加速器第五期招募启动 - 来和SegmentFault 成为加速器校友吧

微软创投加速器第五期招募启动,各位技术创业的基友们抓住机会申请吧 就在昨天, 2014年4月10日,微软创投加速器宣布正式启动第五期初创企业团队招募,TMT 领域的初创团队即日起即可开始在线申请报名。成功入选的初创企业团队将于2014年7月中旬正式入驻位于北京市中关村微软亚太研发大厦内部的办公空间,在接下来的6个月中,除了你能在高大上的微软加速器办公,还会得到很多附加服务,很多内部私密的培训课程、

gaoyang.devRead article
HHello World: Re-ActHello World: Re-Act·Jan 19, 2014

SegmentFault 团队的价值观以及生产力工具

公司文化,团队价值观 相信技术能让世界变的更美好! 在这里,让你发现科技、技术、编程的美 诚实守信、热爱、开放、透明、有爱、有活力、有干劲 要青春有活力,做事的方式要体现我们年轻人的节奏:我们团队非常的年轻,创始人团队是有一个疯狂滴90后以及两个85后骚年!我们目前的10人团队平均年龄才只有21-23岁! 工作方式 我们特别注重团队成员的长期发展,并认为这是公司长期发展的根基,我们也愿

gaoyang.devRead article
HHello World: Re-ActHello World: Re-Act·Jan 13, 2014

创业公司需要什么样的人才?

上次元旦聚餐的时候,状态不好,没跟员工们一起吹吹牛逼,索性大家当天各种开玩笑还是蛮开心的,最后也做了一个简单的决定,尽量以后在聚餐的饭桌上还是少谈具体工作的事情啦,可以各种欢乐先吐槽! 终于今天(2014年1月10日)上午,我在前一天晚上熬夜整理了一个简单的提纲,跟我们的少年们一起分享一下,自己的一些感受,以及SegmentFault 明年的计划:) 下面是具体的一些分享,希望对大家也有所帮助 :

gaoyang.devRead article

Page 18 of 18 · 324 articles