Recent evidence suggests that deep neural networks (DNNs) are vulnerable to adversarial examples, which are crafted by adding human-imperceptible perturbations to legitimate examples. However, most of the existing adversarial attacks generate adversarial examples with weak transferability, making it difficult to evaluate the robustness of DNNs under the challenging black-box setting. To address this issue, we propose two methods: Nesterov momentum iterative fast gradient sign method (N-MI-FGSM) and scale-invariant attack method (SIM), to improve the transferability of adversarial examples. N-MI-FGSM tries a better optimizer by applying the idea of Nesterov accelerated gradient to gradient-based attack method. SIM leverages the scale-invariant property of DNNs and optimizes the generated adversarial example by a set of scaled images as the inputs. Further, the two methods can be naturally combined to form a strong attack and enhance existing gradient attack methods. Empirical results on ImageNet and NIPS 2017 adversarial competition show that the proposed methods can generate adversarial examples with higher transferability than existing competing baselines.

Different aspects of a clinical sample can be revealed by multiple types of omics data. Integrated analysis of multi-omics data provides a comprehensive view of patients, which has the potential to facilitate more accurate clinical decision making. However, omics data are normally high dimensional with large number of molecular features and relatively small number of available samples with clinical labels. The "dimensionality curse" makes it challenging to train a machine learning model using high dimensional omics data like DNA methylation and gene expression profiles. Here we propose an end-to-end deep learning model called OmiVAE to extract low dimensional features and classify samples from multi-omics data. OmiVAE combines the basic structure of variational autoencoders with a classification network to achieve task-oriented feature extraction and multi-class classification. The training procedure of OmiVAE is comprised of an unsupervised phase without the classifier and a supervised phase with the classifier. During the unsupervised phase, a hierarchical cluster structure of samples can be automatically formed without the need for labels. And in the supervised phase, OmiVAE achieved an average classification accuracy of 97.49% after 10-fold cross-validation among 33 tumour types and normal samples, which shows better performance than other existing methods. The OmiVAE model learned from multi-omics data outperformed that using only one type of omics data, which indicates that the complementary information from different omics datatypes provides useful insights for biomedical tasks like cancer classification.

In recent years, deep neural networks have found success in replicating human-level cognitive skills, yet they suffer from several major obstacles. One significant limitation is the inability to learn new tasks without forgetting previously learned tasks, a shortcoming known as catastrophic forgetting. In this research, we propose a simple method to overcome catastrophic forgetting and enable continual learning in neural networks. We draw inspiration from principles in neurology and physics to develop the concept of weight friction. Weight friction operates by a modification to the update rule in the gradient descent optimization method. It converges at a rate comparable to that of the stochastic gradient descent algorithm and can operate over multiple task domains. It performs comparably to current methods while offering improvements in computation and memory efficiency.

If you ask any group of data science students about the types of machine learning algorithms, they will answer without hesitation: supervised and unsupervised. However, if we ask that same group to list different types of unsupervised learning, we are likely to get an answer like clustering but not much more. While supervised methods lead the current wave of innovation in areas such as deep learning, there is very little doubt that the future of artificial intelligence(AI) will transition towards more unsupervised forms of learning. In recent years, we have seen a lot of progress on several new forms of unsupervised learning methods that expand way beyond traditional clustering or principal component analysis(PCA) techniques. Today, I would like to explore some of the most prominent new schools of thought in the unsupervised space and their role in the future of AI.

The beach offers a wide open playscape where children are fuelled by curiosity. Whether at the beach or elsewhere outdoors, it helps to take a moment to see the world through the lens of a child who is discovering the world anew, and slow down to be present. Part of what happens through children's play is the exhilaration of making choices. These choices, and their consequences, are part of the child's emerging sense of agency and identity. Children's inquisitive minds crave opportunities that allow them to become designers, builders, mathematicians and innovators of their world.

Convolutional Neural Networks (CNNs) are often described as black boxes due to the difficulty in explaining how they reach their final output for a given task. Consequently a number of techniques have been developed to aid in the process of explainability. These techniques range from the scoring of individual pixels to reflect their impact on the networks decision making, to the scoring of larger regions of the image. Scoring larger regions allows for the results to be more easily interpreted. A popular technique for explaining images is LIME [10]. This uses superpixels, contiguous regions for visualisation, allowing a level of interpretability that may not be present in individual pixel scoring. However, this increased interpretability comes at a cost. The LIME technique relies on perturbing the input image and repeatedly passing it to the network to build an understanding of how important each superpixel region is to the final classification. This requires multiple perturbed images to be passed through the network, by default 1000 in the released code.

Deep learning methods operate in regimes that defy the traditional statistical mindset. The neural network architectures often contain more parameters than training samples, and are so rich that they can interpolate the observed labels, even if the latter are replaced by pure noise. Despite their huge complexity, the same architectures achieve small generalization error on real data. This phenomenon has been rationalized in terms of a so-called `double descent' curve. As the model complexity increases, the generalization error follows the usual U-shaped curve at the beginning, first decreasing and then peaking around the interpolation threshold (when the model achieves vanishing training error). However, it descends again as model complexity exceeds this threshold. The global minimum of the generalization error is found in this overparametrized regime, often when the number of parameters is much larger than the number of samples. Far from being a peculiar property of deep neural networks, elements of this behavior have been demonstrated in much simpler settings, including linear regression with random covariates. In this paper we consider the problem of learning an unknown function over the $d$-dimensional sphere $\mathbb S^{d-1}$, from $n$ i.i.d. samples $(\boldsymbol x_i, y_i) \in \mathbb S^{d-1} \times \mathbb R$, $i \le n$. We perform ridge regression on $N$ random features of the form $\sigma(\boldsymbol w_a^{\mathsf T}\boldsymbol x)$, $a \le N$. This can be equivalently described as a two-layers neural network with random first-layer weights. We compute the precise asymptotics of the generalization error, in the limit $N, n, d \to \infty$ with $N/d$ and $n/d$ fixed. This provides the first analytically tractable model that captures all the features of the double descent phenomenon.

The importance of training robust neural network grows as 3D data is increasingly utilized in deep learning for vision tasks, like autonomous driving. We examine this problem from the perspective of the attacker, which is necessary in understanding how neural networks can be exploited, and thus defended. More specifically, we propose adversarial attacks based on solving different optimization problems, like minimizing the perceptibility of our generated adversarial examples, or maintaining a uniform density distribution of points across the adversarial object surfaces. Our four proposed algorithms for attacking 3D point cloud classification are all highly successful on existing neural networks, and we find that some of them are even effective against previously proposed point removal defenses.

Training accurate deep neural networks (DNNs) in the presence of noisy labels is an important and challenging task. Though a number of approaches have been proposed for learning with noisy labels, many open issues remain. In this paper, we show that DNN learning with Cross Entropy (CE) exhibits overfitting to noisy labels on some classes ("easy" classes), but more surprisingly, it also suffers from significant under learning on some other classes ("hard" classes). Intuitively, CE requires an extra term to facilitate learning of hard classes, and more importantly, this term should be noise tolerant, so as to avoid overfitting to noisy labels. Inspired by the symmetric KL-divergence, we propose the approach of \textbf{Symmetric cross entropy Learning} (SL), boosting CE symmetrically with a noise robust counterpart Reverse Cross Entropy (RCE). Our proposed SL approach simultaneously addresses both the under learning and overfitting problem of CE in the presence of noisy labels. We provide a theoretical analysis of SL and also empirically show, on a range of benchmark and real-world datasets, that SL outperforms state-of-the-art methods. We also show that SL can be easily incorporated into existing methods in order to further enhance their performance.

Deep learning is a popular machine learning technique and has been applied to many real-world problems. However, training a deep neural network is very time-consuming, especially on big data. It has become difficult for a single machine to train a large model over large datasets. A popular solution is to distribute and parallelize the training process across multiple machines using the parameter server framework. In this paper, we present a distributed paradigm on the parameter server framework called Dynamic Stale Synchronous Parallel (DSSP) which improves the state-of-the-art Stale Synchronous Parallel (SSP) paradigm by dynamically determining the staleness threshold at the run time. Conventionally to run distributed training in SSP, the user needs to specify a particular staleness threshold as a hyper-parameter. However, a user does not usually know how to set the threshold and thus often finds a threshold value through trial and error, which is time-consuming. Based on workers' recent processing time, our approach DSSP adaptively adjusts the threshold per iteration at running time to reduce the waiting time of faster workers for synchronization of the globally shared parameters, and consequently increases the frequency of parameters updates (increases iteration throughput), which speedups the convergence rate. We compare DSSP with other paradigms such as Bulk Synchronous Parallel (BSP), Asynchronous Parallel (ASP), and SSP by running deep neural networks (DNN) models over GPU clusters in both homogeneous and heterogeneous environments. The results show that in a heterogeneous environment where the cluster consists of mixed models of GPUs, DSSP converges to a higher accuracy much earlier than SSP and BSP and performs similarly to ASP. In a homogeneous distributed cluster, DSSP has more stable and slightly better performance than SSP and ASP, and converges much faster than BSP.