Pre-trained language models have made significant strides in natural language processing tasks, enabling flexible fine-tuning for downstream applications. However, in few-shot learning scenarios, pre-trained models face challenges related to overfitting due to limited training samples, which hinders their ability to capture data diversity and robustly handle input variations. To overcome these limitations, we propose the Saliency-Augmented Consistency Regularization (SACR) framework, a novel self-training strategy designed to improve few-shot learning performance and robustness. SACR consists of three key components: (1) Saliency-guided Data Perturbation, which uses saliency analysis to identify and perturb words that significantly influence model predictions, generating semantically consistent pseudo-samples; (2) Semantic-equivalent Sample Mining, which employs K-means clustering to select semantically similar samples and prevent semantic shift; and (3) Consistency Training, where regularization ensures consistency between the semantics and prediction distributions of the original and perturbed samples. We conducted extensive experiments on 15 public datasets to evaluate our approach. SACR significantly outperforms strong baseline models and demonstrates superior generalization capabilities compared to state-of-the-art methods, achieving an average 1.0% improvement in classification accuracy.

With the advantages of high mobility and flexible deployment, Unmanned Aerial Vehicle (UAV) combines with Mobile Edge Computing (MEC) is a promising technology. When dynamic Terminal Users (TUs) offload tasks to UAVs, eavesdroppers may eavesdrop on the channel information. The offloading decisions, trajectory plannings of UAVs and resource allocation with the objective of high-capacity secure communication is a challenging problem. In this paper, we design a multi-UAVs MEC system, where the original region is divided into several sub-regions and TUs offload tasks to UAVs which provide computing services for these TUs. Meanwhile, A joint optimization problem of offloading decision, resource allocation and trajectory planning is formulated, where TUs move with the Gauss-Markov random model. In addition, the Base Station (BS) emits jamming signals to evade the eavesdropping of offloading information from eavesdroppers. The goal of the optimization problem is to maximize the TUs’ minimum secure calculation capacity, and a Joint Dynamic Programming and Bidding (JDPB) algorithm is proposed to solve it. The Successive Convex Approximation (SCA) and Block Coordinate Descent (BCD) algorithms are used to handle the resource allocation and trajectory planning problems, and the bidding method is used to address the task offloading decision problem. Simulation results show that JDPB has better performance and better robustness under different parameter settings than other schemes.

In linguistics, the uncertainty of context due to polysemy is widespread, which attracts much attention. Quantum-inspired complex word embedding based on Hilbert space plays an important role in natural language processing (NLP), which fully leverages the similarity between quantum states and word tokens. A word containing multiple meanings could correspond to a single quantum particle which may exist in several possible states, and a sentence could be analogous to the quantum system where particles interfere with each other. Motivated by quantum-inspired complex word embedding, interpretable complex-valued word embedding (ICWE) is proposed to design two end-to-end quantum-inspired deep neural networks (ICWE-QNN and CICWE-QNN representing convolutional complex-valued neural network based on ICWE) for binary text classification. They have the proven feasibility and effectiveness in the application of NLP and can solve the problem of text information loss in CE-Mix [1] model caused by neglecting the important linguistic features of text, since linguistic feature extraction is presented in our model with deep learning algorithms, in which gated recurrent unit (GRU) extracts the sequence information of sentences, attention mechanism makes the model focus on important words in sentences and convolutional layer captures the local features of projected matrix. The model ICWE-QNN can avoid random combination of word tokens and CICWE-QNN fully considers textual features of the projected matrix. Experiments conducted on five benchmarking classification datasets demonstrate our proposed models have higher accuracy than the compared traditional models including CaptionRep BOW, DictRep BOW and Paragram-Phrase, and they also have great performance on F1-score. Eespecially, CICWE-QNN model has higher accuracy than the quantum-inspired model CE-Mix as well for four datasets including SST, SUBJ, CR and MPQA. It is a meaningful and effictive exploration to design quantum-inspired deep neural networks to promote the performance of text classification.

A quantum circuit learning approach is studied to carry out the fast-fitting of Gaussian functions. First, a parameterized structure is designed for quantum circuits based on the boson sampling model. And then, the training procedure of exploiting gradient-based optimizations is presented to iteratively update the gradient of the loss function concerning circuit parameters. For efficiency, two kinds of circuit loss, the kernel maximum mean discrepancy and the mean absolute error, are used in the training procedure, which are both competent to achieve quantum circuit learning well. It is significant that the two circuit losses assist in reducing the variance to$2.54 \times 10^{-6}$and$6.91 \times 10^{-6}$, respectively. Finally, a kind of quantum circuit fixed structure is developed with the boson sampling model that can decrease the model complexity as the circuit depth d grows. Sets of experiments have been conducted to evaluate the proposed quantum circuit learning scheme, and demonstrate that our parameterized approach is efficient and promising, and it is worth looking forward to solving practical application problems with quantum computers since valid quantum circuits for Gaussian function fast-fitting can be designed indeed.

Early rehabilitation exercises after elbow fracture treatment can affect the degree of joint function recovery. Due to the different levels of endurance and pain tolerance of patients, blind training not only makes patients to suffer pain, but also tends to cause postoperative complications. Therefore, this paper introduces a wearable assistive elbow rehabilitation training device that can quantify the patient's recovery level. The device uses pressure sensors to collect the pressure value of the patient's arm when squeezing the muscles, tri-axial gyroscopes and tri-axial accelerometers to perceive the angular velocity and acceleration of the patient's arm during the rehabilitation exercise. The collected data are processed by an internal processor and presented in a touch screen, which in turn provides a reference for the physician to develop a rehabilitation training program. In addition, the device also provides voice alerts when the patient's rehabilitation training reaches an unreasonable level or range of motion, helping the patient to carry out quantized rehabilitation training and promote normal fracture healing.