Neuronova SDK — Early Access

This is an early-access release of the Neuronova SDK, designed to give you hands-on access to a new computing paradigm: always-on, ultra-low-power analog AI at the edge.

Some features may be incomplete, APIs may evolve, and parts of the experience will change as the technology matures. This is expected at this stage.

We’re releasing the SDK early on purpose. We believe the fastest way to build the right platform is to build it together with the people who are pushing real application to the real world, not in isolation.

Your feedback is extremely important to us. What works, what doesn’t, what feels missing, all of it directly influences our roadmap, our tooling, and the next iterations of both software and silicon.

This is not just about testing an SDK.
It’s about shaping a new always-on intelligence layer at the edge.

Thank for being with us!

OK

Loss Functions Overview

This section documents the loss functions provided by NWAVE.

The losses are organized into two conceptual families:

1. Network-level losses
   Losses that improve training stability, accuracy, or representational behavior. These are hardware-agnostic and can be used with any spiking or non-spiking network.

2. Hardware-aware regularizers
   Losses designed to account for non-idealities and constraints of the Neuronova neuromorphic chip H1. These losses help produce deployable networks whose parameters comply with hardware limits.

Important consideration

The losses described here represent one possible strategy to obtain hardware-compatible networks. There is no single correct solution: multiple training strategies and regularization schemes may lead to deployable models in an easier way, so is part of the research also to find strategies to reach a deployable configuration of the net.

---

Contents

• Network-level losses
• Hardware-aware losses