We propose a novel regularization method, called \textit{volumization}, for neural networks. Inspired by physics, we define a physical volume for the weight parameters in neural networks, and we show that this method is an effective way of regularizing neural networks. Intuitively, this method interpolates between an $L_2$ and $L_\infty$ regularization. Therefore, weight decay and weight clipping become special cases of the proposed algorithm. We prove, on a toy example, that the essence of this method is a regularization technique to control bias-variance tradeoff. The method is shown to do well in the categories where the standard weight decay method is shown to work well, including improving the generalization of networks and preventing memorization. Moreover, we show that the volumization might lead to a simple method for training a neural network whose weight is binary or ternary.

We study how state-of-the-art neural networks for 3D object detection using a single-stage pipeline can be made safety aware. We start with the safety specification (reflecting the capability of other components) that partitions the 3D input space by criticality, where the critical area employs a separate criterion on robustness under perturbation, quality of bounding boxes, and the tolerance over false negatives demonstrated on the training set. In the architecture design, we consider symbolic error propagation to allow feature-level perturbation. Subsequently, we introduce a specialized loss function reflecting (1) the safety specification, (2) the use of single-stage detection architecture, and finally, (3) the characterization of robustness under perturbation. We also replace the commonly seen non-max-suppression post-processing algorithm by a safety-aware non-max-inclusion algorithm, in order to maintain the safety claim created by the neural network. The concept is detailed by extending the state-of-the-art PIXOR detector which creates object bounding boxes in bird's eye view with inputs from point clouds.

In this manuscript, we provide a structured and comprehensive overview of techniques to integrate machine learning with physics-based modeling. First, we provide a summary of application areas for which these approaches have been applied. Then, we describe classes of methodologies used to construct physics-guided machine learning models and hybrid physics-machine learning frameworks from a machine learning standpoint. With this foundation, we then provide a systematic organization of these existing techniques and discuss ideas for future research.

Recommender systems are software applications that help users to find items of interest in situations of information overload. Current research often assumes a one-shot interaction paradigm, where the users' preferences are estimated based on past observed behavior and where the presentation of a ranked list of suggestions is the main, one-directional form of user interaction. Conversational recommender systems (CRS) take a different approach and support a richer set of interactions. These interactions can, for example, help to improve the preference elicitation process or allow the user to ask questions about the recommendations and to give feedback. The interest in CRS has significantly increased in the past few years. This development is mainly due to the significant progress in the area of natural language processing, the emergence of new voice-controlled home assistants, and the increased use of chatbot technology. With this paper, we provide a detailed survey of existing approaches to conversational recommendation. We categorize these approaches in various dimensions, e.g., in terms of the supported user intents or the knowledge they use in the background. Moreover, we discuss technological approaches, review how CRS are evaluated, and finally identify a number of gaps that deserve more research in the future.

The Obstacle Tower Challenge is the task to master a procedurally generated chain of levels that subsequently get harder to complete. Whereas the top 6 performing entries of last year's competition all used human demonstrations to learn how to cope with the challenge, we present an approach that performed competitively (placed 7th) but starts completely from scratch by means of Deep Reinforcement Learning with a relatively simple feed-forward deep network structure. We especially look at the generalization performance of the taken approach concerning different seeds and various visual themes that have become available after the competition, and investigate where the agent fails and why. Note that our approach does not possess a short-term memory like employing recurrent hidden states. With this work, we hope to contribute to a better understanding of what is possible with a relatively simple, flexible solution that can be applied to learning in environments featuring complex 3D visual input where the abstract task structure itself is still fairly simple.

Data poisoning--the process by which an attacker takes control of a model by making imperceptible changes to a subset of the training data--is an emerging threat in the context of neural networks. Existing attacks for data poisoning have relied on hand-crafted heuristics. Instead, we pose crafting poisons more generally as a bi-level optimization problem, where the inner level corresponds to training a network on a poisoned dataset and the outer level corresponds to updating those poisons to achieve a desired behavior on the trained model. We then propose MetaPoison, a first-order method to solve this optimization quickly. MetaPoison is effective: it outperforms previous clean-label poisoning methods by a large margin under the same setting. MetaPoison is robust: its poisons transfer to a variety of victims with unknown hyperparameters and architectures. MetaPoison is also general-purpose, working not only in fine-tuning scenarios, but also for end-to-end training from scratch with remarkable success, e.g. causing a target image to be misclassified 90% of the time via manipulating just 1% of the dataset. Additionally, MetaPoison can achieve arbitrary adversary goals not previously possible--like using poisons of one class to make a target image don the label of another arbitrarily chosen class. Finally, MetaPoison works in the real-world. We demonstrate successful data poisoning of models trained on Google Cloud AutoML Vision. Code and premade poisons are provided at https://github.com/wronnyhuang/metapoison

Caching of popular content closer to the mobile user can significantly increase overall user experience as well as network efficiency by decongesting backbone network segments in the case of congestion episodes. In order to find the optimal caching locations, many conventional approaches rely on solving a complex optimization problem that suffers from the curse of dimensionality, which may fail to support online decision making. In this paper we propose a framework to amalgamate model based optimization with data driven techniques by transforming an optimization problem to a grayscale image and train a convolutional neural network (CNN) to predict optimal caching location policies. The rationale for the proposed modelling comes from CNN's superiority to capture features in grayscale images reaching human level performance in image recognition problems. The CNN is trained with optimal solutions and numerical investigations reveal that the performance can increase by more than 400% compared to powerful randomized greedy algorithms. To this end, the proposed technique seems as a promising way forward to the holy grail aspect in resource orchestration which is providing high quality decision making in real time.

Interfacing memory with behaviour is crucial for building systems that self-learn. In reinforcement learning, an agent can be an on-policy learner, which can only learn the value of its direct actions, or an off-policy learner, which can learn about optimal actions even when not performing those actions – e.g., it might be taking random actions, but can still learn what the best possible action would be. Off-policy learning is therefore a desirable property for agents, helping them learn the best course of action to take while thoroughly exploring their environment. Combining off-policy learning with memory is challenging because you need to know what you might remember when executing a different behaviour. For example, what you might choose to remember when looking for an apple (e.g., where the apple is located), is different to what you might choose to remember if looking for an orange. But if you were looking for an orange, you could still learn how to find the apple if you came across the apple by chance, in case you need to find it in the future.

Speech-to-text (STT), also known as automated-speech-recognition (ASR), has a long history and has made amazing progress over the past decade. Currently, it is often believed that only large corporations like Google, Facebook, or Baidu (or local state-backed monopolies for the Russian language) can provide deployable "in-the-wild" solutions. Following the success and the democratization (the so-called "ImageNet moment", i.e. the reduction of hardware requirements, time-to-market and minimal dataset sizes to produce deployable products) of computer vision, it is logical to hope that other branches of Machine Learning (ML) will follow suit. The only questions are, when will it happen and what are the necessary conditions for it to happen? If the above conditions are satisfied, one can develop new useful applications with reasonable costs. Also democratization occurs - one no longer has to rely on giant companies such as Google as the only source of truth in the industry.

The explosion of breakthroughs, investments, and entrepreneurial activity around artificial intelligence over the last decade has been driven exclusively by deep learning, a sophisticated statistical analysis technique for finding hidden patterns in large quantities of data. A term coined in 1955--artificial intelligence--was applied (or mis-applied) to deep learning, a more advanced version of an approach to training computers to perform certain tasks--machine learning--a term coined in 1959. The recent success of deep learning is the result of the increased availability of lots of data (big data) and the advent of Graphics Processing Units (GPUs), significantly increasing the breadth and depth of the data used for training computers and reducing the time required for training deep learning algorithms. The technology that animated movies like "Toy Story" and enabled a variety of special effects is the ... [ ] focus of this year's Turing Award, the technology industry's version of the Nobel Prize. The term "big data" first appeared in computer science literature in an October 1997 article by Michael Cox and David Ellsworth, "Application-controlled demand paging for out-of-core visualization," published in the Proceedings of the IEEE 8th conference on Visualization.