Visual odometry (VO) is a prevalent way to deal with the relative localization problem, which is becoming increasingly mature and accurate, but it tends to be fragile under challenging environments. Comparing with classical geometry-based methods, deep learning-based methods can automatically learn effective and robust representations, such as depth, optical flow, feature, ego-motion, etc., from data without explicit computation. Nevertheless, there still lacks a thorough review of the recent advances of deep learning-based VO (Deep VO). Therefore, this paper aims to gain a deep insight on how deep learning can profit and optimize the VO systems. We first screen out a number of qualifications including accuracy, efficiency, scalability, dynamicity, practicability, and extensibility, and employ them as the criteria. Then, using the offered criteria as the uniform measurements, we detailedly evaluate and discuss how deep learning improves the performance of VO from the aspects of depth estimation, feature extraction and matching, pose estimation. We also summarize the complicated and emerging areas of Deep VO, such as mobile robots, medical robots, augmented reality and virtual reality, etc. Through the literature decomposition, analysis, and comparison, we finally put forward a number of open issues and raise some future research directions in this field.

Recent learning techniques for the representation of code depend mostly on human-annotated (labeled) data. In this work, we are proposing Corder, a self-supervised learning system that can learn to represent code without having to label data. The key innovation is that we train the source code model by asking it to recognize similar and dissimilar code snippets through a contrastive learning paradigm. We use a set of semantic-preserving transformation operators to generate snippets that are syntactically diverse but semantically equivalent. The contrastive learning objective, at the same time, maximizes agreement between different views of the same snippets and minimizes agreement between transformed views of different snippets. We train different instances of Corder on 3 neural network encoders, which are Tree-based CNN, ASTNN, and Code2vec over 2.5 million unannotated Java methods mined from GitHub. Our result shows that the Corder pre-training improves code classification and method name prediction with large margins. Furthermore, the code vectors generated by Corder are adapted to code clustering which has been shown to significantly beat the other baselines.

Convolutional and recurrent neural networks have been widely employed to achieve state-of-the-art performance on classification tasks. However, it has also been noted that these networks can be manipulated adversarially with relative ease, by carefully crafted additive perturbations to the input. Though several experimentally established prior works exist on crafting and defending against attacks, it is also desirable to have theoretical guarantees on the existence of adversarial examples and robustness margins of the network to such examples. We provide both in this paper. We focus specifically on recurrent architectures and draw inspiration from dynamical systems theory to naturally cast this as a control problem, allowing us to dynamically compute adversarial perturbations at each timestep of the input sequence, thus resembling a feedback controller. Illustrative examples are provided to supplement the theoretical discussions.

In this work, we present a hardware compatible neural network training algorithm in which we used alternating direction method of multipliers (ADMM) and iterative least-square methods. The motive behind this approach was to conduct a method of training neural networks that is scalable and can be parallelised. These characteristics make this algorithm suitable for hardware implementation. We have achieved 6.9\% and 6.8\% better accuracy comparing to SGD and Adam respectively, with a four-layer neural network with hidden size of 28 on HIGGS dataset. Likewise, we could observe 21.0\% and 2.2\% accuracy improvement comparing to SGD and Adam respectively, on IRIS dataset with a three-layer neural network with hidden size of 8. This is while the use of matrix inversion, which is challenging for hardware implementation, is avoided in this method. We assessed the impact of avoiding matrix inversion on ADMM accuracy and we observed that we can safely replace matrix inversion with iterative least-square methods and maintain the desired performance. Also, the computational complexity of the implemented method is polynomial regarding dimensions of the input dataset and hidden size of the network.

Deep learning has been widely used for supervised learning and classification/regression problems. Recently, a novel area of research has applied this paradigm to unsupervised tasks; indeed, a gradient-based approach extracts, efficiently and autonomously, the relevant features for handling input data. However, state-of-the-art techniques focus mostly on algorithmic efficiency and accuracy rather than mimic the input manifold. On the contrary, competitive learning is a powerful tool for replicating the input distribution topology. This paper introduces a novel perspective in this area by combining these two techniques: unsupervised gradient-based and competitive learning. The theory is based on the intuition that neural networks are able to learn topological structures by working directly on the transpose of the input matrix. At this purpose, the vanilla competitive layer and its dual are presented. The former is just an adaptation of a standard competitive layer for deep clustering, while the latter is trained on the transposed matrix. Their equivalence is extensively proven both theoretically and experimentally. However, the dual layer is better suited for handling very high-dimensional datasets. The proposed approach has a great potential as it can be generalized to a vast selection of topological learning tasks, such as non-stationary and hierarchical clustering; furthermore, it can also be integrated within more complex architectures such as autoencoders and generative adversarial networks.

Spectral normalization (SN) is a widely-used technique for improving the stability of Generative Adversarial Networks (GANs) by forcing each layer of the discriminator to have unit spectral norm. This approach controls the Lipschitz constant of the discriminator, and is empirically known to improve sample quality in many GAN architectures. However, there is currently little understanding of why SN is so effective. In this work, we show that SN controls two important failure modes of GAN training: exploding and vanishing gradients. Our proofs illustrate a (perhaps unintentional) connection with the successful LeCun initialization technique, proposed over two decades ago to control gradients in the training of deep neural networks. This connection helps to explain why the most popular implementation of SN for GANs requires no hyperparameter tuning, whereas stricter implementations of SN have poor empirical performance out-of-the-box. Unlike LeCun initialization which only controls gradient vanishing at the beginning of training, we show that SN tends to preserve this property throughout training. Finally, building on this theoretical understanding, we propose Bidirectional Spectral Normalization (BSN), a modification of SN inspired by Xavier initialization, a later improvement to LeCun initialization. Theoretically, we show that BSN gives better gradient control than SN. Empirically, we demonstrate that BSN outperforms SN in sample quality on several benchmark datasets, while also exhibiting better training stability.

It is well established that neural networks are vulnerable to adversarial examples, which are almost imperceptible on human vision and can cause the deep models misbehave. Such phenomenon may lead to severely inestimable consequences in the safety and security critical applications. Existing defenses are trend to harden the robustness of models against adversarial attacks, e.g., adversarial training technology. However, these are usually intractable to implement due to the high cost of re-training and the cumbersome operations of altering the model architecture or parameters. In this paper, we discuss the saliency map method from the view of enhancing model interpretability, it is similar to introducing the mechanism of the attention to the model, so as to comprehend the progress of object identification by the deep networks. We then propose a novel method combined with additional noises and utilize the inconsistency strategy to detect adversarial examples. Our experimental results of some representative adversarial attacks on common datasets including ImageNet and popular models show that our method can detect all the attacks with high detection success rate effectively. We compare it with the existing state-of-the-art technique, and the experiments indicate that our method is more general.

While distributed training significantly speeds up the training process of the deep neural network (DNN), the utilization of the cluster is relatively low due to the time-consuming data synchronizing between workers. To alleviate this problem, a novel Hierarchical Parallel SGD (HPSGD) strategy is proposed based on the observation that the data synchronization phase can be paralleled with the local training phase (i.e., Feed-forward and back-propagation). Furthermore, an improved model updating method is unitized to remedy the introduced stale gradients problem, which commits updates to the replica (i.e., a temporary model that has the same parameters as the global model) and then merges the average changes to the global model. Extensive experiments are conducted to demonstrate that the proposed HPSGD approach substantially boosts the distributed DNN training, reduces the disturbance of the stale gradients and achieves better accuracy in given fixed wall-time.

Evaluation of students' performance for the completion of courses has been a major problem for both students and faculties during the work-from-home period in this COVID pandemic situation. To this end, this paper presents an in-depth analysis of deep learning and machine learning approaches for the formulation of an automated students' performance estimation system that works on partially available students' academic records. Our main contributions are (a) a large dataset with fifteen courses (shared publicly for academic research) (b) statistical analysis and ablations on the estimation problem for this dataset (c) predictive analysis through deep learning approaches and comparison with other arts and machine learning algorithms. Unlike previous approaches that rely on feature engineering or logical function deduction, our approach is fully data-driven and thus highly generic with better performance across different prediction tasks.

Recent years have witnessed the popularity of Graph Neural Networks (GNN) in various scenarios. To obtain optimal data-specific GNN architectures, researchers turn to neural architecture search (NAS) methods, which have made impressive progress in discovering effective architectures in convolutional neural networks. Two preliminary works, GraphNAS and Auto-GNN, have made first attempt to apply NAS methods to GNN. Despite the promising results, there are several drawbacks in expressive capability and search efficiency of GraphNAS and Auto-GNN due to the designed search space. To overcome these drawbacks, we propose the SNAG framework (Simplified Neural Architecture search for Graph neural networks), consisting of a novel search space and a reinforcement learning based search algorithm. Extensive experiments on real-world datasets demonstrate the effectiveness of the SNAG framework compared to human-designed GNNs and NAS methods, including GraphNAS and Auto-GNN.