When a satellite performs complex tasks such as discarding a payload or capturing a non-cooperative target, it will encounter sudden changes in the attitude and mass parameters, causing unstable flying and rolling of the satellite. In such circumstances, the change of the movement and mass characteristics are unpredictable. Thus, the traditional attitude control methods are unable to stabilize the satellite since they are dependent on the mass parameters of the controlled object. In this paper, we proposed a reinforcement learning method to re-stabilize the attitude of a satellite under such circumstances. Specifically, we discretize the continuous control torque, and build a neural network model that can output the discretized control torque to control the satellite. A dynamics simulation environment of the satellite is built, and the deep Q Network algorithm is then performed to train the neural network in this simulation environment. The reward of the training is the stabilization of the satellite. Simulation experiments illustrate that, with the iteration of training progresses, the neural network model gradually learned to re-stabilize the attitude of a satellite after unknown disturbance. As a contrast, the traditional PD (Proportion Differential) controller was unable to re-stabilize the satellite due to its dependence on the mass parameters. The proposed method adopts self-learning to control satellite attitudes, shows considerable intelligence and certain universality, and has a strong application potential for future intelligent control of satellites performing complex space tasks.

Embedded computing platforms such as neural network accelerators deploying neural network models need to quantize the values into low-bit integers through quantization operations. However, most current embedded computing platforms with a fixed-point architecture do not directly support performing the quantization operation for the LSTM layer. Meanwhile, the influence of sequential input data for LSTM has not been taken into account by quantization algorithms. Aiming at these two technical bottlenecks, a new sequential-characteristics-based operators disassembly quantization method for LSTM layers is proposed. Specifically, the calculation process of the LSTM layer is split into multiple regular layers supported by the neural network accelerator. The quantization-parameter-generation process is designed as a sequential-characteristics-based combination strategy for sequential and diverse image groups. Therefore, LSTM is converted into multiple mature operators for single-layer quantization and deployed on the neural network accelerator. Comparison experiments with the state of the art show that the proposed quantization method has comparable or even better performance than the full-precision baseline in the field of character-/word-level language prediction and image classification applications. The proposed method has strong application potential in the subsequent addition of novel operators for future neural network accelerators.

Integrated Development Environments (IDEs) help increase programmer productivity by automating much clerical and administrative work. Thus, it is of great research and practical interest to learn about the characteristics on how IDE features change and mature. To this end, we have conducted an empirical study, analyzing a total of 645 ldquoWhat's Newrdquo release note entries in 7 releases of the Eclipse IDE both quantitatively and qualitatively. It is found that majority of the changes are refinements or incremental additions to the feature architecture set up in early releases (1.0 and 2.0). Motivated by this, a further analysis on usability is performed to characterize how these changes impact programmers effectiveness in using the IDE. We summarize our study methodology and lessons learned.

Quantization reduces the precision of neural network parameters to accelerate inference and lower power consumption, but it often causes noticeable accuracy degradation. We propose a differentiable quantization framework that replaces the non-differentiable rounding operation with a continuous surrogate function. During QAT, gradients are backpropagated through the proposed surrogate rather than being estimated by the STE, enabling gradient-based optimization of model weights, quantization parameters, and layer-wise bit-width configurations. Experiments on CIFAR-10 show that our method achieves higher accuracy than several representative quantization approximation methods under different bit-width settings. On embedded platforms, it improves post-quantization accuracy by up to 3.66 percentage points over industrial quantization frameworks such as TensorRT and Huawei AMCT on detection and segmentation tasks, and outperforms representative bit-width allocation methods by up to 7.49 percentage points. These results demonstrate the effectiveness of the proposed method for improving the accuracy of quantized neural networks on resource-constrained devices.