Consistently checking the statistical significance of experimental results is one of the mandatory methodological steps to address the so-called "reproducibility crisis" in deep reinforcement learning. In this tutorial paper, we explain how the number of random seeds relates to the probabilities of statistical errors. For both the t-test and the bootstrap confidence interval test, we recall theoretical guidelines to determine the number of random seeds one should use to provide a statistically significant comparison of the performance of two algorithms. Finally, we discuss the influence of deviations from the assumptions usually made by statistical tests. We show that they can lead to inaccurate evaluations of statistical errors and provide guidelines to counter these negative effects. We make our code available to perform the tests.

While accelerators such as GPUs have limited memory, deep neural networks are becoming larger and will not fit with the memory limitation of accelerators for training. We propose an approach to tackle this problem by rewriting the computational graph of a neural network, in which swap-out and swap-in operations are inserted to temporarily store intermediate results on CPU memory. In particular, we first revise the concept of a computational graph by defining a concrete semantics for variables in a graph. We then formally show how to derive swap-out and swap-in operations from an existing graph and present rules to optimize the graph. To realize our approach, we developed a module in TensorFlow, named TFLMS. TFLMS is published as a pull request in the TensorFlow repository for contributing to the TensorFlow community. With TFLMS, we were able to train ResNet-50 and 3DUnet with 4.7x and 2x larger batch size, respectively. In particular, we were able to train 3DUNet using images of size of $192^3$ for image segmentation, which, without TFLMS, had been done only by dividing the images to smaller images, which affects the accuracy.

Novel data acquisition schemes have been an emerging need for scanning microscopy based imaging techniques to reduce the time in data acquisition and to minimize probing radiation in sample exposure. Varies sparse sampling schemes have been studied and are ideally suited for such applications where the images can be reconstructed from a sparse set of measurements. Dynamic sparse sampling methods, particularly supervised learning based iterative sampling algorithms, have shown promising results for sampling pixel locations on the edges or boundaries during imaging. However, dynamic sampling for imaging skeleton-like objects such as metal dendrites remains difficult. Here, we address a new unsupervised learning approach using Hierarchical Gaussian Mixture Mod- els (HGMM) to dynamically sample metal dendrites. This technique is very useful if the users are interested in fast imaging the primary and secondary arms of metal dendrites in solidification process in materials science.

Active learning is relevant and challenging for high-dimensional regression models when the annotation of the samples is expensive. Yet most of the existing sampling methods cannot be applied to large-scale problems, consuming too much time for data processing. In this paper, we propose a fast active learning algorithm for regression, tailored for neural network models. It is based on uncertainty estimation from stochastic dropout output of the network. Experiments on both synthetic and real-world datasets show comparable or better performance (depending on the accuracy metric) as compared to the baselines. This approach can be generalized to other deep learning architectures. It can be used to systematically improve a machine-learning model as it offers a computationally efficient way of sampling additional data.

We introduce Explainable Learning, ExL, an approach for training neural networks that are intrinsically robust to adversarial attacks. We find that the implicit generative modelling of random noise, during posterior maximization, improves a model's understanding of the data manifold furthering adversarial robustness. We prove our approach's efficacy and provide a simplistic visualization tool for understanding adversarial data, using Principal Component Analysis. Our analysis reveals that adversarial robustness, in general, manifests in models with higher variance along the high-ranked principal components. We show that models learnt with ExL perform remarkably well against a wide-range of black-box attacks.

We present a representation learning algorithm that learns a low-dimensional latent dynamical system from high-dimensional sequential raw data, e.g., video. The framework builds upon recent advances in amortized inference methods that use both an inference network and a refinement procedure to output samples from a variational distribution given an observation sequence, and takes advantage of the duality between control and inference to approximately solve the intractable inference problem using the path integral control approach. The learned dynamical model can be used to predict and plan the future states; we also present the efficient planning method that exploits the learned low-dimensional latent dynamics. Numerical experiments show that the proposed path-integral control based variational inference method leads to tighter lower bounds in statistical model learning of sequential data. The supplementary video can be found at https://youtu.be/4jDcbuAJ7mA.

In this paper we propose two novel bounds for the log-likelihood based on Kullback-Leibler and the R\'{e}nyi divergences, which can be used for variational inference and in particular for the training of Variational AutoEncoders. Our proposal is motivated by the difficulties encountered in training VAEs on continuous datasets with high contrast images, such as those with handwritten digits and characters, where numerical issues often appear unless noise is added, either to the dataset during training or to the generative model given by the decoder. The new bounds we propose, which are obtained from the maximization of the likelihood of an interval for the observations, allow numerically stable training procedures without the necessity of adding any extra source of noise to the data.

Data is the fuel that drives the machine learning algorithmic engines and ultimately provides the business value. In his session at Cloud Expo, Ed Featherston, a director and senior enterprise architect at Collaborative Consulting, discussed the key considerations around quality, volume, timeliness, and pedigree that must be dealt with in order to properly fuel that engine. Speaker Bio Ed Featherston is a director/senior enterprise architect at Collaborative Consulting. He brings 35 years of technology experience in designing, building, and implementing large complex solutions. He has significant expertise in systems integration, Internet/intranet, and cloud technologies, Ed has delivered projects in various industries, including financial services, pharmacy, government and retail.

When you step off the train here and walk into the city square outside the railway station, you will not see the spires of King's College Chapel or the turrets atop the Trinity Great Court. The University of Cambridge is still a cab ride away. But you will see a stone and glass office building with a rooftop patio. This is where Amazon designs its flying drones. Just down the block, inside a stone building of its own, Microsoft is designing some sort of computer chip for artificial intelligence.

SNK is celebrating its 40th birthday with a triumphant return to the golden age of arcade games -- with a modern twist. On November 13, the creator is launching a bevy of retro games for Nintendo Switch, including Alpha Mission, Ikari Warriors, Athena, Guerrilla War and Vanguard, among others. There's more to be announced, too, although the titles already confirmed can be pre-ordered now as part of the Switch-exclusive pack. Also part of its anniversary celebrations is the Neo Geo mini, a pocket-sized video game console boasting 40 vintage arcade titles that faithfully reproduce the Neo Geo arcade cabinet that was introduced in Japan in 1990. No word yet on the release date and title line up, but it'll likely be this year, and it will certainly be old-school awesome.