Rain has envisioned a new roadmap for artificial intelligence hardware that is intended to bring us from the expensive digital AI of today to efficient, brain scale intelligence. Digital AI – deep learning – has been fundamentally enabled by two pillar technologies. These are a learning algorithm, backpropagation, and a scaling architecture, the GPU. Rain has developed these two pillar technologies for a new roadmap. Their learning algorithm is called equilibrium propagation, and performs learning through gradient descent with fundamental physics. Their scaling architecture is called the Neuromorphic Processing Unit, or NPU. The NPU consists of analog neurons that are tiled across the chip surface creating a high-density CMOS neuromorphic processor. Instantiating millions of artificial neurons in a square centimeter enables massive neural networks to fit onto a single chip. ‘The memristor is recognized as an ideal artificial synapse. Memristor is a combination of “memory” and “resistor”; it is a resistor capable of changing its resistance. On top of their grid of neurons, they deposit layers of these memristor synapses, exploiting sparsity to mimic connectivity patterns observed in the brain. This combination of a novel learning algorithm and scaling architecture allows Rain to envision a product roadmap that outperforms status quo hardware in speed, power, form factor, and scalability.