Techniques for optimizing neural networks

A system, comprising:

• one or more processors to cause data generated by one or more layers of a neural network to be cached and reused by the neural network;
• and
• one or more memories to store the cached data.

A machine-readable medium having stored thereon a set of instructions, which if performed by one or more processors, cause the one or more processors to at least:

• cache data generated by one or more layers of a neural network;
• and
• reuse the cached data by the neural network.

A method, comprising:

• caching data generated by one or more layers of a neural network;
• and
• reusing the cached data by the neural network.

A vehicle, comprising:

• one or more sensors to generate sensor data;
• and
• one or more processors to generate a prediction based, at least in part, on inferencing with a neural network using the sensor data as an input, caching data generated by one or more layers of the neural network, and reusing the cached values in the neural network.