Photo by Circe Denyer on PublicDomainPictures.netUsually, when I see BatchNorm and Dropout layers in a neural network, I don’t pay them much attention. I tend to think of them as simple means to speed up training and improve generalization with no side effects when the network is in inference mode. In this post, I will show why this notion is not always correct, and may cause the neural network to

What if we could go back to 1965, knock on Abbey Road Studios’ front door holding an ‘All Access’ badge, and have the privilege of listening to those signature Lennon-McCartney harmonies A-Capella? Our input here is a medium quality mp3 of We Can Work it Out by The Beatles. The top track is the input mix and the bottom track, the isolated vocals coming out of our model. Formally known as Audio Sou

Donkey Car in action with teleoperation control panel in the unity simulatorIn this post, we will see how to train an autonomous racing car in minutes and how to smooth its control. The method, based on Reinforcement Learning (RL) and presented here in simulation (Donkey Car simulator), was designed to be applicable in the real world. It builds on the work of a startup named Wayve.ai that focuses

With the rise of autonomous vehicles, smart video surveillance, facial detection and various people counting applications, fast and accurate object detection systems are rising in demand. These systems involve not only recognizing and classifying every object in an image, but localizing each one by drawing the appropriate bounding box around it. This makes object detection a significantly harder t

Suppose I gave you the title of an article “Amazing Flat version of Twitter Bootstrap” and asked you which publication that article appeared in: the New York Times, TechCrunch, or GitHub. What would be your guess? How about an article titled “Supreme Court to Hear Major Case on Partisan Districts”? Did you guess GitHub and New York Times? Why? Words like Twitter and Major are likely to occur in an