/explore

Click through on any links that interest you or select the planets on the right to continue exploring the Outer Web.
You are here

 robotchinwag.com
Gradients of Matrix Multiplication in Deep Learning | Robot Chinwag
| | dennybritz.com
Recurrent Neural Networks Tutorial, Part 3 - Backpropagation Through Time and Vanishing Gradients ยท Denny's Blog
2.6 parsecs away

Travel
| | This the thirdpart of the Recurrent Neural Network Tutorial.
| | liorsinai.github.io
Backpropagation through a layer norm - Lior Sinai
3.1 parsecs away

Travel
| | Derivation of the backpropagation equations for layer normalization.
| | marcospereira.me
Backpropagation From Scratch-Marcos Pereira
2.2 parsecs away

Travel
| | In this post we summarize the math behind deep learning and implement a simple network that achieves 85% accuracy classifying digits from the MNIST dataset.
| | entangledlogs.com
Quaternions | Entangled Logs
22.3 parsecs away

Travel
| To visualize quaternions in the fanciest way, visit Ben eater, Quaternion. Euler angles suffer from a problem of gimbal lock. When rotating around a 3-perpendicular axis in euclidean space, if either two of these axes align i.e becomes parallel, it causes gimbal lock. Once the object is locked, the object will lose one degree of freedom for rotation. This video provides an intuitive explanation of the problem. Pitfalls When converting the Euler angle to a quaternion, it will lose some information.