Face recognition with Google's FaceNet deep neural network.

AI Expert Roadmap

Roadmap to becoming an Artificial Intelligence Expert in 2022

Machine Learning for Software Engineers, by Nam Vu

A complete daily plan for studying to become a machine learning engineer.

Microsoft Recommenders

Best Practices on Recommendation Systems

Google deepdream - Neural Network art

DeepDream is an experimental project from Google Research that explores neural network visualization through artistic image generation. It complements a research blog post about "Inceptionism" and demonstrates how convolutional neural networks can be used to create psychedelic, dream-like imagery by amplifying patterns detected in images. ## Key Features - **Neural Network Art Generation** — Uses trained convolutional neural networks to transform images by enhancing detected patterns - **IPython Notebook Implementation** — Provides executable sample code in a Jupyter notebook format for easy experimentation - **Pattern Amplification** — Applies gradient ascent to amplify features that neural networks recognize in input images - **Research Demonstration** — Serves as a practical implementation of the techniques described in Google's neural network visualization research ## Philosophy DeepDream represents an artistic exploration of neural network internals, treating AI models as creative tools that can generate novel visual patterns through algorithmic pareidolia.