Zuken’s eCADSTAR now includes design constraint management for length-, delay-, and skew-based routing.
Zuken’s eCADSTAR now includes design constraint management for length-, delay-, and skew-based routing.
This article presents the equations that we use when performing weight-update computations, and we’ll also discuss the…
This article presents the equations that we use when performing weight-update computations, and we’ll also discuss the concept of backpropagation.
This New Product Brief (NPB) is part of a video series highlighting the features, applications, and technical specs of…
This New Product Brief (NPB) is part of a video series highlighting the features, applications, and technical specs of newly-released products.
The XCVU13P module incorporates 52 multi-gigabit transceivers for stable performance up to 32.75Gbps.
The XCVU13P module incorporates 52 multi-gigabit transceivers for stable performance up to 32.75Gbps.
We can greatly enhance the performance of a Perceptron by adding a layer of hidden nodes, but those hidden nodes also…
We can greatly enhance the performance of a Perceptron by adding a layer of hidden nodes, but those hidden nodes also make training a bit more complicated.
In this article, we’ll see why we need a new activation function for a neural network that is trained via gradient descent.
In this article, we’ll see why we need a new activation function for a neural network that is trained via gradient descent.
This article explains why high-performance neural networks need an extra “hidden” layer of computational nodes.
This article explains why high-performance neural networks need an extra “hidden” layer of computational nodes.
In a bid to galvanize its own AI future, Intel has acquired advanced AI training and inference silicon technology.
In a bid to galvanize its own AI future, Intel has acquired advanced AI training and inference silicon technology.
This article discusses learning rate, which plays an important role in neural-network training.
This article discusses learning rate, which plays an important role in neural-network training.
This New Product Brief (NPB) is part of a video series highlighting the features, applications, and technical specs of…
This New Product Brief (NPB) is part of a video series highlighting the features, applications, and technical specs of newly-released products.
This article presents an algorithm intended for humans to calibrate the internal oscillator of an MCU, with the help of…
This article presents an algorithm intended for humans to calibrate the internal oscillator of an MCU, with the help of an oscilloscope and a spreadsheet. An example experiment with numbers is also shown.
Intel’s Horse Ridge chip is expected to speed up the development of commercially viable quantum computers and burn a…
Intel’s Horse Ridge chip is expected to speed up the development of commercially viable quantum computers and burn a path to scaling larger systems.
Microchip's new RISC-V-based PolarFire SoC family is said to provide 50% lower power than competing mid-range FPGAs.
Microchip's new RISC-V-based PolarFire SoC family is said to provide 50% lower power than competing mid-range FPGAs.
The new kit offers out-of-the-box support for full desktop Linux and is compatible with many peripherals that support 4K,…
The new kit offers out-of-the-box support for full desktop Linux and is compatible with many peripherals that support 4K, including Ethernet, USB, and HDMI.
In this article, we’ll explore Perceptron training from a more theoretical perspective, focusing on the “error bowl.”
In this article, we’ll explore Perceptron training from a more theoretical perspective, focusing on the “error bowl.”
Groq, a semiconductor startup with software roots, has developed a new processing unit with a unique architecture that…
Groq, a semiconductor startup with software roots, has developed a new processing unit with a unique architecture that offers inference solutions for AI acceleration.
This Featured Product Spotlight is part of a video series exploring the specifications, applications, and market context…
This Featured Product Spotlight is part of a video series exploring the specifications, applications, and market context of new products.
In this article, we’ll review some important aspects of neural-net training, and then we’ll discuss the concept of…
In this article, we’ll review some important aspects of neural-net training, and then we’ll discuss the concept of overtraining.
This article presents Python code that allows you to automatically generate weights for a simple neural network.
This article presents Python code that allows you to automatically generate weights for a simple neural network.
The platform supports 5G applications at the edge through a Single Pane of Glass—the automated management of thousands…
The platform supports 5G applications at the edge through a Single Pane of Glass—the automated management of thousands of nodes.