量子神经网络中的过度参数化理论
Martín Larocca1,2, Nathan Ju3, Diego García-Martín3,4,5
1Theoretical Division, Los Alamos National Laboratory, Los Alamos, NM, USA. larocca@lanl.gov.
Nature computational science
|January 4, 2024
概括
量子神经网络 (QNN) 的过度参数化通过消除局部最小值来提高可训练性. 这发生在参数数量超过关键值时,从而提高QNN的容量和性能.
科学领域:
- 量子计算是一种量子计算.
- 机器学习 机器学习
- 人工智能的人工智能
背景情况:
- 量子神经网络 (QNN) 为实现量子优势提供了一个有希望的途径.
- 了解QNN属性的影响,如参数计数,对损失景观对于可扩展架构设计至关重要.
研究的目的:
- 严格分析QNN中的过度参数化现象.
- 为了定义过度参数化的关键参数值 (M_c).
- 研究过度参数化,可训练性和QNN能力之间的关系.
主要方法:
- 对QNN中的过度参数化现象的分析.
- 基于超过关键数量的参数 (M_c) 的过度参数化的定义.
- 数学推导,将李代数的维度与M_c和矩阵等级相关.
主要成果:
- 李代数的维度为M_c提供了一个上限.
- M_c决定了量子费舍尔信息和黑斯矩阵的最大等级.
- 低参数化QNN中的虚假局部最小值在M >= M_c时消失,这表明可训练性得到改善.
结论:
- 在QNN中超参数化开始意味着计算阶段过渡,提高可训练性.
- 过度参数化的QNN达到其最大容量.
- 这项研究为设计高效和可扩展的QNN架构提供了关键的见解.
相关概念视频
Neural Circuits
1.2K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
1.2K
The Quantum-Mechanical Model of an Atom
42.3K
Shortly after de Broglie published his ideas that the electron in a hydrogen atom could be better thought of as being a circular standing wave instead of a particle moving in quantized circular orbits, Erwin Schrödinger extended de Broglie’s work by deriving what is now known as the Schrödinger equation. When Schrödinger applied his equation to hydrogen-like atoms, he was able to reproduce Bohr’s expression for the energy and, thus, the Rydberg formula governing hydrogen spectra.
42.3K
Parallel Processing
152
The brain processes sensory information rapidly due to parallel processing, which involves sending data across multiple neural pathways at the same time. This method allows the brain to manage various sensory qualities, such as shapes, colors, movements, and locations, all concurrently. For instance, when observing a forest landscape, the brain simultaneously processes the movement of leaves, the shapes of trees, the depth between them, and the various shades of green. This enables a quick and...
152
Neuroplasticity
364
Neuroplasticity reflects the brain's remarkable capacity to adapt and evolve, responding dynamically to learning, experiences, or injury by reorganizing its neural circuitry. This reorganization involves creating new neural connections and refining old ones through a series of biological processes that contribute to the brain's lifelong development and adaptability.
364
Neural Regulation
39.5K
Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.
39.5K
The Role of Ion Channels in Neuronal Computation
3.2K
A postsynaptic neuron usually receives numerous impulses from several other presynaptic neurons. The axon hillock of the postsynaptic neuron integrates all these signals and determines the likelihood of firing an action potential.
Sometimes a single EPSP is strong enough to induce an action potential in the postsynaptic neuron. However, multiple presynaptic inputs must often create EPSPs around the same time for the postsynaptic neuron to be sufficiently depolarized to fire an action potential....
Sometimes a single EPSP is strong enough to induce an action potential in the postsynaptic neuron. However, multiple presynaptic inputs must often create EPSPs around the same time for the postsynaptic neuron to be sufficiently depolarized to fire an action potential....
3.2K


