MAX78000 MCU, 32-bit, 512 KB, BGA-81 (8x8mm)

The MAX78000 is a new breed of AI microcontroller that enables neural networks to be deployed where they are needed.
The extremely low power consumption, combined with the energy-efficient AI processing enables with the CNN )convolutuinal neural network) and battery operation of AI applications.

The advanced SOC is built on a modern Arm® Cortex®-M4 MCU with FPU, further contains a RISC microcontroller for economical signal processing and a CNN with a weight memory of 442 KB.

The CNN architecture is highly flexible, and networks can be trained using traditional toolsets such as PyTorch TensorFlow® and then converted using tools provided by Maxim.

Special features

- ultra-low-power microcontroller with two cores
- Arm Cortex-M4 processor with FPU up to 100MHz
- 512KB Flash and 128KB SRAM
- 32-bit RISC-V coprocessor with up to 60MHz
- Neural Network Accelerator
- Highly optimized for deep convolutional neural networks
- 442k 8bit weight capacity with 1,2,4,8-bit weights
- programmable input image size up to 1024 x 1024 pixels
- programmable network depth up to 64 layers
- programmable network channel widths per layer
- security and integrity
- available secure boot
- AES 128/192/256 hardware acceleration module
- True Random Number Generator (TRNG)