Zindi is convening Africa's data scientists to create AI solutions for complex problems. Founded in 2018, the Cape Town-based startup allows companies, NGOs or government institutions to host online competitions around data-oriented challenges. Zindi's platform also coordinates a group of more than 4,000 data scientists based in Africa who can enroll to join a competition, submit their solution sets, move up a leader board and win the challenge -- for a cash prize payout. The highest purse so far has been $12,000, split across the top three data scientists in a competition, according to Zindi co-founder Celina Lee. Competition hosts receive the results, which they can use to create new products or integrate into their existing systems and platforms. Zindi's model has gained the attention of some big corporate names in and outside of Africa.

Neural networks trained with backpropagation, the standard algorithm of deep learning which uses weight transport, are easily fooled by existing gradient-based adversarial attacks. This class of attacks are based on certain small perturbations of the inputs to make networks misclassify them. We show that less biologically implausible deep neural networks trained with feedback alignment, which do not use weight transport, can be harder to fool, providing actual robustness. Tested on MNIST, deep neural networks trained without weight transport (1) have an adversarial accuracy of 98% compared to 0.03% for neural networks trained with backpropagation and (2) generate non-transferable adversarial examples. However, this gap decreases on CIFAR-10 but still significant particularly for small perturbation magnitude less than 1/2.

--In this paper, a method of prediction on continuous time series variables from the production or flow - an LSTM algorithm based on multivariate tuning - is proposed. The algorithm improves the traditional LSTM algorithm and converts the time series data into supervised learning sequences regarding industrial data's features. The main innovation of this paper consists in introducing the concepts of periodic measurement and time window in the industrial prediction problem, especially considering industrial data with time series characteristics. Experiments using real-world datasets show that the prediction accuracy is improved, 54.05% higher than that of traditional LSTM algorithm. In industry, with the high-speed functioning of the enterprise product line, data are generated continuously. Malfunctions and abnormality often take place, which incur a great deal of money and resources, and even advanced equipment cannot avoid these problems[1]. Industrial companies have to pay a lot to maintain and ensure the normal operation of the manufacturing process. According to the statistics, the maintenance costs of all kinds of industrial enterprises account for about 15%-70% of total production costs[2]. Flow prediction is motivated by such industrial conundrums faced by many factories. Implementing flow prediction to forecast the output of the machine and to detect the problems in time via prediction, not only can production increase, but also a large number of workforce and resources for troubleshooting can be saved.

Deep neural networks achieve state-of-the-art results on several tasks while increasing in complexity. It has been shown that neural networks can be pruned during training by imposing sparsity inducing regularizers. In this paper, we investigate two techniques for group-wise pruning during training in order to improve network efficiency. We propose a gating factor after every convolutional layer to induce channel level sparsity, encouraging insignificant channels to become exactly zero. Further, we introduce and analyse a bounded variant of the L1 regularizer, which interpolates between L1 and L0-norms to retain performance of the network at higher pruning rates. To underline effectiveness of the proposed methods,we show that the number of parameters of ResNet-164, DenseNet-40 and MobileNetV2 can be reduced down by 30%, 69% and 75% on CIFAR100 respectively without a significant drop in accuracy. We achieve state-of-the-art pruning results for ResNet-50 with higher accuracy on ImageNet. Furthermore, we show that the light weight MobileNetV2 can further be compressed on ImageNet without a significant drop in performance.

Path-planning algorithms are an important part of a wide variety of robotic applications, such as mobile robot navigation and robot arm manipulation. However, in large search spaces in which local traps may exist, it remains challenging to reliably find a path while satisfying real-time constraints. Efforts to speed up the path search have led to the development of many practical path-planning algorithms. These algorithms often define a search heuristic to guide the search towards the goal. The heuristics should be carefully designed for each specific problem to ensure reliability in the various situations encountered in the problem. However, it is often difficult for humans to craft such robust heuristics, and the search performance often degrades under conditions that violate the heuristic assumption. Rather than manually designing the heuristics, in this work, we propose a learning approach to acquire these search heuristics. Our method represents the environment containing the obstacles as an image, and this image is fed into fully convolutional neural networks to produce a search heuristic image where every pixel represents a heuristic value (cost-to-go value to a goal) in the form of a vertex of a search graph. Training the heuristic is performed using previously collected planning results. Our preliminary experiments (2D grid world navigation experiments) demonstrate significant reduction in the search costs relative to a hand-designed heuristic.

Work integrating conversations around AI and Disability is vital and valued, particularly when done through a lens of fairness. Yet at the same time, analyzing the ethical implications of AI for disabled people solely through the lens of a singular idea of "fairness" risks reinforcing existing power dynamics, either through reinforcing the position of existing medical gatekeepers, or promoting tools and techniques that benefit otherwise-privileged disabled people while harming those who are rendered outliers in multiple ways. In this paper we present two case studies from within computer vision - a subdiscipline of AI focused on training algorithms that can "see" - of technologies putatively intended to help disabled people but, through failures to consider structural injustices in their design, are likely to result in harms not addressed by a "fairness" framing of ethics. Drawing on disability studies and critical data science, we call on researchers into AI ethics and disability to move beyond simplistic notions of fairness, and towards notions of justice.

The majority of contemporary object-tracking approaches used in autonomous vehicles do not model interactions between objects. This contrasts with the fact that objects' paths are not independent: a cyclist might abruptly deviate from a previously planned trajectory in order to avoid colliding with a car. Building upon HART, a neural, class-agnostic single-object tracker, we introduce a multi-object tracking method MOHART capable of relational reasoning. Importantly, the entire system, including the understanding of interactions and relations between objects, is class-agnostic and learned simultaneously in an end-to-end fashion. We find that the addition of relational-reasoning capabilities to HART leads to consistent performance gains in tracking as well as future trajectory prediction on several real-world datasets (MOTChallenge, UA-DETRAC, and Stanford Drone dataset), particularly in the presence of ego-motion, occlusions, crowded scenes, and faulty sensor inputs. Finally, based on controlled simulations, we propose that a comparison of MOHART and HART may be used as a novel way to measure the degree to which the objects in a video depend upon each other as they move together through time.

Variational inference is becoming more and more popular for approximating intractable posterior distributions in Bayesian statistics and machine learning. Meanwhile, a few recent works have provided theoretical justification and new insights on deep neural networks for estimating smooth functions in usual settings such as nonparametric regression. In this paper, we show that variational inference for sparse deep learning retains the same generalization properties than exact Bayesian inference. In particular, we highlight the connection between estimation and approximation theories via the classical bias-variance trade-off and show that it leads to near-minimax rates of convergence for H\"older smooth functions. Additionally, we show that the model selection framework over the neural network architecture via ELBO maximization does not overfit and adaptively achieves the optimal rate of convergence.

Activation functions play a key role in providing remarkable performance in deep neural networks, and the rectified linear unit (ReLU) is one of the most widely used activation functions. Various new activation functions and improvements on ReLU have been proposed, but each carry performance drawbacks. In this paper, we propose an improved activation function, which we name the natural-logarithm-rectified linear unit (NLReLU). This activation function uses the parametric natural logarithmic transform to improve ReLU and is simply defined as. NLReLU not only retains the sparse activation characteristic of ReLU, but it also alleviates the "dying ReLU" and vanishing gradient problems to some extent. It also reduces the bias shift effect and heteroscedasticity of neuron data distributions among network layers in order to accelerate the learning process. The proposed method was verified across ten convolutional neural networks with different depths for two essential datasets. Experiments illustrate that convolutional neural networks with NLReLU exhibit higher accuracy than those with ReLU, and that NLReLU is comparable to other well-known activation functions. NLReLU provides 0.16% and 2.04% higher classification accuracy on average compared to ReLU when used in shallow convolutional neural networks with the MNIST and CIFAR-10 datasets, respectively. The average accuracy of deep convolutional neural networks with NLReLU is 1.35% higher on average with the CIFAR-10 dataset.

Penalized (or regularized) regression, as represented by Lasso and its variants, has become a standard technique for analyzing high-dimensional data when the number of variables substantially exceeds the sample size. The performance of penalized regression relies crucially on the choice of the tuning parameter, which determines the amount of regularization and hence the sparsity level of the fitted model. The optimal choice of tuning parameter depends on both the structure of the design matrix and the unknown random error distribution (variance, tail behavior, etc). This article reviews the current literature of tuning parameter selection for high-dimensional regression from both theoretical and practical perspectives. We discuss various strategies that choose the tuning parameter to achieve prediction accuracy or support recovery. We also review several recently proposed methods for tuning-free high-dimensional regression.