CNN Output Size Formula

CNN Output Size Formula

In this video, deeplizard debugs the forward method and review the tensor shape transformations as well as the formula to calculate convolution output size. Details
Best Practices for Preparing and Augmenting Image Data for Convolutional Neural Networks

Best Practices for Preparing & Augmenting Images for Convolutional Neural Networks

Here's an interesting tutorial on prepping image data for CNNs. It is challenging to know how to best prepare image data when training a convolutional... Details
Exploring And Attacking Neural Networks with Activation Atlases

Exploring And Attacking Neural Networks with Activation Atlases

Two Minute Papers has a look at neural networks, visualization, and how they really work under the hood. Check out this site to explore the... Details
Forward Propagation Explained

Forward Propagation Explained

In this video, deeplizard shows how to use a convolutional neural network (CNN) to generate an output prediction tensor from a sample image of a... Details
Is Deep Learning Just Neural Networks on Steroids?

Is Deep Learning Just Neural Networks on Steroids?

Here's an interesting and skeptical walk through of neural networks vs deep neural networks and what, if anything, makes them different. Here's an  excerpt: The... Details
How to Avoid Overfitting in Deep Learning Neural Networks

How to Avoid Overfitting in Deep Learning Neural Networks

Here's a great article on avoiding overfitting in deep neural networks. No one is too legit to overfit. Training a deep neural network that can... Details
In praise of the autoencoder

In Praise of the Autoencoder

Of all the machine learning algorithms, the most fascinating are neural networks. They don't require statistical hypothesis or rigorous data preparation save for normalization. The... Details
Deep Learning with TensorFlow and Intel - a hardware and software guide for beginners

Deep Learning with TensorFlow and Intel – a hardware and software guide for beginners

Deep learning is central to recent innovations in AI. If you don't want to run your code in the cloud and prefer to build your... Details
Artificial Intelligence Beyond Deep Neural Networks

Artificial Intelligence Beyond Deep Neural Networks

Here's an interesting look at the cutting edge technologies just on the horizon of AI research and what problems they can potentially solve that current... Details
Physicists train the oscillatory neural network to recognize images

Physicists Train Oscillatory Neural Network to Recognize Images

Here's an interesting article on "oscillatory neural networks" and how physicists trained it to perform image recognition. An oscillatory neural network is a complex interlacing... Details