Regularization for Neural Networks with Framingham Case Study
L1, L2, elastic net, and group lasso regularization
作者：Rachel Lea Ballantyne Draelos 来源：medium
发布时间：2019-06-09 21:13:48
A Simple Introduction to K-Nearest Neighbors Algorithm
What is KNN?
作者：Dhilip Subramanian 来源：medium
发布时间：2019-06-09 08:53:55
Meta Learning — AI Generalised.
AI learning to learn, to help with learning from few “shots”.
作者：Snehal Reddy Koukuntla 来源：medium
发布时间：2019-06-09 05:14:11
Using reinforcement learning to trade Bitcoin for massive profit
Let’s teach our deep RL agents to make even more money through feature engineering and Bayesian optimization
作者：Adam King 来源：medium
发布时间：2019-06-09 03:29:19
How To Get Funding For AI Startups
After having worked with several VCs and startups, I noticed that successful startups tend to share the same elements. I wanted to write…
作者：Alexandre Gonfalonieri 来源：medium
发布时间：2019-06-08 17:48:56
How do you check the quality of your regression model in Python?
Linear regression is rooted strongly in statistical learning and therefore the model must be checked for the ‘goodness of fit.
作者：Tirthajyoti Sarkar 来源：medium
发布时间：2019-06-08 02:34:20
DeepTweets: Generating Fake Tweets with Neural Networks Trained on Individual Twitter Accounts
I fine-tuned the GPT-2 model on tweets from people’s Twitter accounts to create AI versions of them & then had the bots rewrite real…
作者：Lex Fridman 来源：medium
发布时间：2019-06-08 02:26:42
VisualData: A Search Engine for Computer Vision Datasets
Algorithms, computation and visual data are the three pillars of computer vision (CV). Researchers, institutions and open source…
作者：Synced 来源：medium
发布时间：2019-06-08 01:14:19
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Since AlexNet won the 2012 ImageNet competition, CNNs (short for Convolutional Neural Networks) have become the de facto algorithms for a…
作者：Aakash Nain 来源：medium
发布时间：2019-06-08 00:21:32
One LEGO at a Time Explaining the Math of how Neural Networks Learn with Implementation from…
A neural network is a clever arrangement of linear and non-linear modules. When we choose and connect them wisely, we have a powerful tool…
作者：Omar U. Florez 来源：medium
发布时间：2019-06-07 23:34:50
1000x Faster Data Augmentation
Population Based Augmentation: Quickly and efficiently learn a state-of-the-art approach to augmenting data for neural network training.
作者：Daniel Ho 来源：medium
发布时间：2019-06-07 21:12:23
GPT2, Counting Consciousness and the Curious Hacker
Disclaimer: I would like it to be made very clear that I am absolutely 100% open to the idea that I am wrong about anything in this post…
作者：Connor Leahy 来源：medium
发布时间：2019-06-07 17:59:10
Modeling the Unseen
How Instacart uses Machine Learning to spot lost demand in its fulfillment chain
作者：Ganesh Krishnan 来源：medium
发布时间：2019-06-07 07:28:35
Basic Statistics Every Data Scientist Should Know
Statistics for data science teams and leadership
作者：SeattleDataGuy 来源：medium
发布时间：2019-06-07 00:52:05
Replicating GPT2–1.5B
In this post, I want to quickly talk about the technical and organizational questions around my recent replication of GPT2–1.5B. Please…
作者：Connor Leahy 来源：medium
发布时间：2019-06-06 23:39:14