Efficient and quantum-adaptive machine learning with fermion neural networks
This work addresses the problem of adapting machine learning to quantum systems for researchers in quantum physics and machine learning, though it appears incremental by building on classical neural networks with quantum-specific adaptations.
The authors tackled the challenge of applying neural networks to quantum systems by proposing fermion neural networks (FNNs), which use physical properties as outputs and achieved competitive performance on machine-learning benchmarks. They demonstrated that FNNs can precisely determine topological phases and emergent charge orders in quantum systems, offering advantages like general connectivity and insights into gradient problems.
Classical artificial neural networks have witnessed widespread successes in machine-learning applications. Here, we propose fermion neural networks (FNNs) whose physical properties, such as local density of states or conditional conductance, serve as outputs, once the inputs are incorporated as an initial layer. Comparable to back-propagation, we establish an efficient optimization, which entitles FNNs to competitive performance on challenging machine-learning benchmarks. FNNs also directly apply to quantum systems, including hard ones with interactions, and offer in-situ analysis without preprocessing or presumption. Following machine learning, FNNs precisely determine topological phases and emergent charge orders. Their quantum nature also brings various advantages: quantum correlation entitles more general network connectivity and insight into the vanishing gradient problem, quantum entanglement opens up novel avenues for interpretable machine learning, etc.