Image Recognition

• Part inspection
• Object recognition
• Face recognition
• Target tracking
• Video monitoring
• Kinematics
• More…

Signal Recognition

• Speech recognition
• Radar identification
• EKG, EEG monitoring
• Sonar identification
• Vibration monitoring
• More…

The CogniMem neural network implements two powerful non-linear classifiers (RCE and KNN) in a natively parallel architecture. The tremendous benefit of this architecture is a recognition cycle which remains under 11 us @ 27 MHz. If the real-time recognition engine built into the chip is running, the data received on the digital input bus is automatically broadcasted to the neurons and the response of the neuron with the best match is available within less than 11 microseconds after the feed of the last data.

CM1K neural network

• Parallel architecture with 1024 neurons
• RCE (Restricted Coulomb Energy)
• Two classifiers:
  Radial Basis Function (RBF)
  K-Nearest Neighbor (KNN) classifier
• Vector data: up to 256 bytes
• Classification status: Identified (pin 13) Uncertain (pin 14) or Unknown
• Categories: up to 32768 values
• Distance calculation: L1 or LSup distance norms
• Sub-networks: up to 127 context values Trained by example
• Recognition stage for direct digital input

Connectivity

• Serial bus I2C (100 kbit, 400 kbit and 3.3Mbit)

Electrical / mechanical

• 300 mW @ 27 MHz
• 3.3 V I/O operation 1.2 V core supply
• Dimensions 40 x 32 x 10 mm

Module pin assignment

For more information, you can download some documentations from HERE.

Purchase The CM-PM1K Prototyping