International Business Machines

How IBM Uses Resistive Memory Chips to Speed Up AI Training

A method for running AI neural networks directly on specialized hardware chips that store data as electrical resistance, making them faster and more energy-efficient than standard processors.

How to Fix Faulty Memory Cells in AI Chips

This patent describes a system that tests individual memory cells in AI chips for uneven behavior and then permanently disables the faulty ones before the chip starts learning, making AI training more efficient.

How a Single Electronic Component Can Learn and Process AI Data

This patent describes a tiny electronic component called a resistive processing unit (RPU) that acts like a brain cell in an artificial intelligence network, storing and processing information directly within its changing electrical resistance.

Attaching Flexible Circuits with Light Sensors to a Chip

This patent describes a method and device for attaching a bendable circuit, which includes light-sensing or light-emitting components, onto a main chip, allowing light to pass through a hole in the chip to reach the flexible part.