Hey! In this issue: recovering an editable 3D object from a photo, music that responds to your feelings, a tutorial on support vector machines, a visual introduction to the structure of a neural network, liabilities and risks associated with AI, and more.

• AutoSweep: recovering 3D editable objects from a single photograph (paper, video)

• AI could generate music on the fly to respond to your feelings

• Podcast: identifying and mitigating liabilities and risks associated with AI

• DeepFaceDrawing generates photorealistic portraits from freehand sketches

• A tutorial on Support Vector Machines

• Stochastic Weight Averaging, a simple procedure that improves generalization in deep learning is now part of PyTorch 1.6

• A visual introduction to the structure of a neural network (plus an awesome video)

• A clarification of misconceptions, myths and desired status of artificial intelligence

• An overview of deep learning architectures in the few-shot learning domain

• Grading on a curve? Why AI systems test brilliantly but stumble in real life

Enjoy the newsletter? Help us make it bigger and better by sharing with your colleagues and friends.