Neural network pruning---the task of reducing the size of a network by removing parameters---has been the subject of a great deal of work in recent years. We provide a meta-analysis of the literature, including an overview of approaches to pruning and consistent findings in the literature. After aggregating results across 81 papers and pruning hundreds of models in controlled conditions, our clearest finding is that the community suffers from a lack of standardized benchmarks and metrics. This deficiency is substantial enough that it is hard to compare pruning techniques to one another or determine how much progress the field has made over the past three decades. To address this situation, we identify issues with current practices, suggest concrete remedies, and introduce ShrinkBench, an open-source framework to facilitate standardized evaluations of pruning methods. We use ShrinkBench to compare various pruning techniques and show that its comprehensive evaluation can prevent common pitfalls when comparing pruning methods.

Deep Neural Network (DNN) suffers from noisy labeled data because of the heavily overfitting risk. To avoid the risk, in this paper, we propose a novel sample selection framework for learning noisy samples. The core idea is to employ a "regret" minimization approach. The proposed sample selection method adaptively selects a subset of noisy-labeled training samples to minimize the regret to select noise samples. The algorithm efficiently works and performs with theoretical support. Moreover, unlike the typical approaches, the algorithm does not require any side information or learning information depending on the training settings of DNN. The experimental results demonstrate that the proposed method improves the performance of a black-box DNN with noisy labeled data.

The prediction horizon demonstrated has been about half dozen Lyapunov time. Is it possible to significantly extend the prediction time beyond what has been achieved so far? We articulate a scheme incorporating time-dependent but sparse data inputs into reservoir computing and demonstrate that such rare "updates" of the actual state practically enable an arbitrarily long prediction horizon for a variety of chaotic systems. A physical understanding based on the theory of temporal synchronization is developed. Starting from the same initial condition, a well-trained reservoir system can generate a trajectory that stays close to that of the target system for a finite amount of time, realizing short-term prediction.

Distributed training is useful to train complicated models to shorten the training time. As each of the workers only sees a small fraction of data, workers need to synchronize on the parameter updates. One of the central questions in distributed training is how to parsimoniously synchronize parameters while preserving model quality. To address this problem, we propose the \textbf{ShadowSync} framework, in which we isolate synchronization from training and run it in the background. In contrast to common strategies including synchronous stochastic gradient descent (SGD), asynchronous SGD, and model averaging on independently trained sub-models, where synchronization happens in the foreground, ShadowSync synchronization is neither part of the backward pass, nor happens every $k$ iterations. Our framework is generic to host various types of synchronization algorithms, and we propose 3 approaches under this theme. The superiority of ShadowSync is confirmed by experiments on training deep neural networks for click-through-rate prediction. Our methods all succeed in making the training throughput linearly scale with the number of trainers. Comparing to their foreground counterparts, our methods exhibit neutral to better model quality and better scalability when we keep the number of parameter servers the same. In our training system which expresses both replication and Hogwild parallelism, ShadowSync also accomplishes the highest example level parallelism number comparing to the prior arts.

Machine learning research has advanced in multiple aspects, including model structures and learning methods. The effort to automate such research, known as AutoML, has also made significant progress. However, this progress has largely focused on the architecture of neural networks, where it has relied on sophisticated expert-designed layers as building blocks---or similarly restrictive search spaces. Our goal is to show that AutoML can go further: it is possible today to automatically discover complete machine learning algorithms just using basic mathematical operations as building blocks. We demonstrate this by introducing a novel framework that significantly reduces human bias through a generic search space. Despite the vastness of this space, evolutionary search can still discover two-layer neural networks trained by backpropagation. These simple neural networks can then be surpassed by evolving directly on tasks of interest, e.g. CIFAR-10 variants, where modern techniques emerge in the top algorithms, such as bilinear interactions, normalized gradients, and weight averaging. Moreover, evolution adapts algorithms to different task types: e.g., dropout-like techniques appear when little data is available. We believe these preliminary successes in discovering machine learning algorithms from scratch indicate a promising new direction for the field.

Additive Manufacturing (AM) is a crucial component of the smart industry. In this paper, we propose an automated quality grading system for the AM process using a deep convolutional neural network (CNN) model. The CNN model is trained offline using the images of the internal and surface defects in the layer-by-layer deposition of materials and tested online by studying the performance of detecting and classifying the failure in AM process at different extruder speeds and temperatures. The model demonstrates the accuracy of 94% and specificity of 96%, as well as above 75% in three classifier measures of the Fscore, the sensitivity, and precision for classifying the quality of the printing process in five grades in real-time. The proposed online model adds an automated, consistent, and non-contact quality control signal to the AM process that eliminates the manual inspection of parts after they are entirely built. The quality monitoring signal can also be used by the machine to suggest remedial actions by adjusting the parameters in real-time. The proposed quality predictive model serves as a proof-of-concept for any type of AM machines to produce reliable parts with fewer quality hiccups while limiting the waste of both time and materials.

In this paper we explore speaker identification using electroencephalography (EEG) signals. The performance of speaker identification systems degrades in presence of background noise, this paper demonstrates that EEG features can be used to enhance the performance of speaker identification systems operating in presence and absence of background noise. The paper further demonstrates that in presence of high background noise, speaker identification system using only EEG features as input demonstrates better performance than the system using only acoustic features as input.

The classical development of neural networks has been primarily for mappings between a finite-dimensional Euclidean space and a set of classes, or between two finite-dimensional Euclidean spaces. The purpose of this work is to generalize neural networks so that they can learn mappings between infinite-dimensional spaces (operators). The key innovation in our work is that a single set of network parameters, within a carefully designed network architecture, may be used to describe mappings between infinite-dimensional spaces and between different finite-dimensional approximations of those spaces. We formulate approximation of the infinite-dimensional mapping by composing nonlinear activation functions and a class of integral operators. The kernel integration is computed by message passing on graph networks. This approach has substantial practical consequences which we will illustrate in the context of mappings between input data to partial differential equations (PDEs) and their solutions. In this context, such learned networks can generalize among different approximation methods for the PDE (such as finite difference or finite element methods) and among approximations corresponding to different underlying levels of resolution and discretization. Experiments confirm that the proposed graph kernel network does have the desired properties and show competitive performance compared to the state of the art solvers.

Protecting the networks of tomorrow is set to be a challenging domain due to increasing cyber security threats and widening attack surfaces created by the Internet of Things (IoT), increased network heterogeneity, increased use of virtualisation technologies and distributed architectures. This paper proposes SDS (Software Defined Security) as a means to provide an automated, flexible and scalable network defence system. SDS will harness current advances in machine learning to design a CNN (Convolutional Neural Network) using NAS (Neural Architecture Search) to detect anomalous network traffic. SDS can be applied to an intrusion detection system to create a more proactive and end-to-end defence for a 5G network. To test this assumption, normal and anomalous network flows from a simulated environment have been collected and analyzed with a CNN. The results from this method are promising as the model has identified benign traffic with a 100% accuracy rate and anomalous traffic with a 96.4% detection rate. This demonstrates the effectiveness of network flow analysis for a variety of common malicious attacks and also provides a viable option for detection of encrypted malicious network traffic.

One of the challenging aspects of applying machine learning is the need to identify the algorithms that will perform best for a given dataset. This process can be difficult, time consuming and often requires a great deal of domain knowledge. We present Sommelier, an expert system for recommending the machine learning algorithms that should be applied on a previously unseen dataset. Sommelier is based on word embedding representations of the domain knowledge extracted from a large corpus of academic publications. When presented with a new dataset and its problem description, Sommelier leverages a recommendation model trained on the word embedding representation to provide a ranked list of the most relevant algorithms to be used on the dataset. We demonstrate Sommelier's effectiveness by conducting an extensive evaluation on 121 publicly available datasets and 53 classification algorithms. The top algorithms recommended for each dataset by Sommelier were able to achieve on average 97.7% of the optimal accuracy of all surveyed algorithms.