Computer Sciences

A new approximate computing approach using CNNs

Researchers at Fukuoka University, in Japan, have recently proposed a design methodology for configurable approximate arithmetic circuits. As part of their study, published on ResearchGate, they applied their method to a ...

Computer Sciences

Computer vision in the dark using recurrent CNNs

Over the past few years, classical convolutional neural networks (cCNNs) have led to remarkable advances in computer vision. Many of these algorithms can now categorize objects in good quality images with high accuracy.

Computer Sciences

WaveGlow: A flow-based generative network to synthesize speech

A team of researchers at NVIDIA has recently developed WaveGlow, a flow-based network that can generate high-quality speech from melspectrograms, which are acoustic time-frequency representations of sound. Their method, outlined ...

Computer Sciences

ColorUNet: A new deep CNN classification approach to colorization

A team of researchers at Stanford University has recently developed a CNN classification method to colorize grayscale images. The tool they devised, called ColorUNet, draws inspiration from U-Net, a fully convolutional network ...

Hardware

USB form neural compute stick makes debut at developer event

Intel has unveiled the Intel Neural Compute Stick 2. It looks like a standard USB thumb drive, and it runs on a USB 3.0 port, but is oh-more-special. CNET said the new AI "brain" sticks into the side of your PC.

Computer Sciences

Using deep neural networks to hunt malicious TLS certificates

A team of researchers at Cyxtera Technologies has recently proposed a neural network-based method for identifying malicious use of web certificates. Their approach, outlined in a paper published in ACM Digital Library, uses ...

Computer Sciences

Finding people in video based on height, cloth color, gender

A special search approach lets you find people in surveillance video just based on their description. The RT headline read, "AI algorithm can find you in CCTV footage without using face recognition." But how? Height, gender, ...

page 1 from 16