Enabling On-Device Self-Supervised Contrastive Learning With Selective Data Contrast

Abstract

After a model is deployed on edge devices, it is desirable for these devices to learn from unlabeled data to continuously improve accuracy. Contrastive learning has demonstrated its great potential in learning from unlabeled data. However, the online input data are usually none independent and identically distributed (non-iid) and edge devices' storages are usually too limited to store enough representative data from different data classes. We propose a framework to automatically select the most representative data from the unlabeled input stream, which only requires a small data buffer for dynamic learning. Experiments show that accuracy and learning speed are greatly improved.

Exploration of Quantum Neural Architecture by Mixing Quantum Neuron Designs

“…Goal 3: The quantum architecture could be trained on classical computers correctly and efficiently. Although training DNN on classical computers is expensive and inefficient [46]- [48], we still have to train QNN on classical computers because the near-term quantum computer (NISQ) has a limited number of qubits and high noise on each qubit, resulting in the QNN training on quantum computers being unstable and not scalable. A straightforward way to achieve the equivalent training on classical computers is to formulate each quantum gate as a unitary matrix.…”