Profile cover photo
Profile photo
Jan Teichmann
6,007 followers -
Don't let perfect be the enemy of good
Don't let perfect be the enemy of good

6,007 followers
About
Jan's posts

Post has shared content
DeepMind just published a mind blowing paper: PathNet.

"Potentially describing how general artificial intelligence will look like.

Since scientists started building and training neural networks, Transfer Learning has been the main bottleneck. Transfer Learning is the ability of an AI to learn from different tasks and apply its pre-learned knowledge to a completely new task. It is implicit that with this precedent knowledge, the AI will perform better and train faster than de novo neural networks on the new task.

DeepMind is on the path of solving this with PathNet. PathNet is a network of neural networks, trained using both stochastic gradient descent and a genetic selection method.

PathNet is composed of layers of modules. Each module is a Neural Network of any type, it could be convolutional, recurrent, feedforward and whatnot."

https://medium.com/@thoszymkowiak/deepmind-just-published-a-mind-blowing-paper-pathnet-f72b1ed38d46#.1fegku2mm

Post has attachment
There is great value in data if you think outside the box. Or why Foursquare can predict share prices. 

Post has shared content

Post has shared content
Learn how to create scalable #MachineLearning apps with #ApacheSpark with this free eBook - http://bit.ly/Free-Tech-Learning (available only today).

What You Will Learn:
~ Create your first Spark program in Scala, Java, and Python
~ Set up and configure a development environment for Spark on your own computer, as well as on Amazon EC2
~ Access public machine learning datasets and use Spark to load, process, clean, and transform data
~ Use Spark's machine learning library to implement programs utilizing well-known machine learning models including collaborative filtering, classification, regression, clustering, and dimensionality reduction
~ Write Spark functions to evaluate the performance of your machine learning models
~ Deal with large-scale text data, including feature extraction and using text data as input to your machine learning models
~ Explore online learning methods and use Spark Streaming for online learning and model evaluation
Photo

Post has shared content

Post has shared content

Post has attachment

Post has attachment
Using Trump speak against Trump.

Post has attachment
New album from Goldfrapp with the first single sounding great! So excited!

Post has attachment
Still using an arithmetic mean or standard deviation? This is a must read
Wait while more posts are being loaded