Researchers from KTH Royal Institute of Technology and Stanford University have now fabricated a material for computer components that enable the commercial viability of computers that mimic the human brain. Electrochemical random access (ECRAM) memory components made with 2D titanium carbide showed outstanding potential for complementing classical transistor technology, and contributing toward commercialization of powerful computers that are modeled after the brain's neural network. Such neuromorphic computers can be thousands times more energy efficient than today's computers. These advances in computing are possible because of some fundamental differences from the classic computing architecture in use today, and the ECRAM, a component that acts as a sort of synaptic cell in an artificial neural network, says KTH Associate Professor Max Hamedi. "Instead of transistors that are either on or off, and the need for information to be carried back and forth between the processor and memory -- these new computers rely on components that can have multiple states, and perform in-memory computation," Hamedi says.

Devices with tunable resistance are highly sought after for neuromorphic computing. Conventional resistive memories, however, suffer from nonlinear and asymmetric resistance tuning and excessive write noise, degrading artificial neural network (ANN) accelerator performance. Emerging electrochemical random-access memories (ECRAMs) display write linearity, which enables substantially faster ANN training by array programing in parallel. However, state-of-the-art ECRAMs have not yet demonstrated stable and efficient operation at temperatures required for packaged electronic devices (~90°C). Here, we show that (semi)conducting polymers combined with ion gel electrolyte films enable solid-state ECRAMs with stable and nearly temperature-independent operation up to 90°C. These ECRAMs show linear resistance tuning over a >2× dynamic range, 20-nanosecond switching, submicrosecond write-read cycling, low noise, and low-voltage (±1 volt) and low-energy (~80 femtojoules per write) operation combined with excellent endurance (>109 write-read operations at 90°C). Demonstration of these high-performance ECRAMs is a fundamental step toward their implementation in hardware ANNs.

What's the best type of device from which to build a neural network? Of course, it should be fast, small, consume little power, have the ability to reliably store many bits-worth of information. And if it's going to be involved in learning new tricks as well as performing those tricks, it has to behave predictably during the learning process. Neural networks can be thought of as a group of cells connected to other cells. These connections--synapses in biological neurons--all have particular strengths, or weights, associated with them. Rather than use the logic and memory of ordinary CPUs to represent these, companies and academic researchers have been working on ways of representing them in arrays of different kinds of nonvolatile memories.