Become a member
Sign in
pegah kamousi
pegah kamousi

pegah kamousi

2 Following
1 Followers
  • Profile
  • Claps
  • Highlights

Highlighted by pegah kamousi

See more

From Deep adversarial learning is finally ready 🚀 and will radically change the game by Michael Dietz

The solution to complexity is abstraction, also known as information hiding. Abstraction is simply the removal of unnecessary detail. The idea is that to design a part of a complex system, you must identify what about that part others must know in order to design their parts, and what details you can hide. The part others must know is the abstraction.

From Semi-supervised learning with Generative Adversarial Networks (GANs) by Thalles Silva

This type of classifier takes a tiny portion of labeled data and a much larger amount of unlabeled data (from the same domain). The goal is to combine these sources of data to train a Deep Convolution Neural Networks (DCNN) to learn an inferred function capable of mapping a new datapoint to its desirable outcome.

From Deep Few-Shot Learning by Tassilo Klein

at contain images … a classifier for different species of birds with only a few labeled objects per category, it might be helpful to exploit other data sources that contain images of birds. In this situation, even unlabel…

Claps from pegah kamousi

See more

Exploratory vs. Exploitative Reading

Tim Beiko

AI-First: Exploring a new era in design

Masha Krol