In machine learning, bigger may not always be better. As the datasets and the machine learning models keep expanding, researchers are racing to build state-of-the-art benchmarks. However, larger models can be detrimental to the budget and the environment. Over time, researchers have developed several ways to shrink the deep learning models while optimizing training datasets. In particular, three techniques–pruning, quantization, and transfer learning–have been instrumental in making models run faster and more accurately at lesser compute power.

Machine learning MLSys 2021: Bridging the divide between machine learning and systems Amazon distinguished scientist and conference general chair Alex Smola on what makes MLSys unique -- both thematically and culturally. Email Alex Smola, Amazon vice president and distinguished scientist The Conference on Machine Learning and Systems ( MLSys), which starts next week, is only four years old, but Amazon scientists already have a rich history of involvement with it. Amazon Scholar Michael I. Jordan is on the steering committee; vice president and distinguished scientist Inderjit Dhillon is on the board and was general chair last year; and vice president and distinguished scientist Alex Smola, who is also on the steering committee, is this year's general chair. As the deep-learning revolution spread, MLSys was founded to bridge two communities that had much to offer each other but that were often working independently: machine learning researchers and system developers. Registration for the conference is still open, with the very low fees of $25 for students and $100 for academics and professionals. "If you look at the big machine learning conferences, they mostly focus on, 'Okay, here's a cool algorithm, and here are the amazing things that it can do. And by the way, it now recognizes cats even better than before,'" Smola says. "They're conferences where people mostly show an increase in capability. At the same time, there are systems conferences, and they mostly care about file systems, databases, high availability, fault tolerance, and all of that. "Now, why do you need something in-between? Well, because quite often in machine learning, approximate is good enough. You don't necessarily need such good guarantees from your systems.

Do you need to classify data or predict outcomes? Are you having trouble getting your machine learning project off the ground? There are a number of techniques available to help you achieve lift-off. Some of the eight methods discussed below will accelerate your machine learning process dramatically, while others will not only accelerate the process but also help you build a better model. Not all of these methods will be suitable for a given project, but the first one--exploratory data analysis--should never be left out.

Building operations represent a significant percentage of the total primary energy consumed in most countries due to the proliferation of Heating, Ventilation and Air-Conditioning (HVAC) installations in response to the growing demand for improved thermal comfort. Reducing the associated energy consumption while maintaining comfortable conditions in buildings are conflicting objectives and represent a typical optimization problem that requires intelligent system design. Over the last decade, different methodologies based on the Artificial Intelligence (AI) techniques have been deployed to find the sweet spot between energy use in HVAC systems and suitable indoor comfort levels to the occupants. This paper performs a comprehensive and an in-depth systematic review of AI-based techniques used for building control systems by assessing the outputs of these techniques, and their implementations in the reviewed works, as well as investigating their abilities to improve the energy-efficiency, while maintaining thermal comfort conditions. This enables a holistic view of (1) the complexities of delivering thermal comfort to users inside buildings in an energy-efficient way, and (2) the associated bibliographic material to assist researchers and experts in the field in tackling such a challenge. Among the 20 AI tools developed for both energy consumption and comfort control, functions such as identification and recognition patterns, optimization, predictive control. Based on the findings of this work, the application of AI technology in building control is a promising area of research and still an ongoing, i.e., the performance of AI-based control is not yet completely satisfactory. This is mainly due in part to the fact that these algorithms usually need a large amount of high-quality real-world data, which is lacking in the building or, more precisely, the energy sector.

We introduce the IBM Analog Hardware Acceleration Kit, a new and first of a kind open source toolkit to simulate analog crossbar arrays in a convenient fashion from within PyTorch (freely available at https://github.com/IBM/aihwkit). The toolkit is under active development and is centered around the concept of an "analog tile" which captures the computations performed on a crossbar array. Analog tiles are building blocks that can be used to extend existing network modules with analog components and compose arbitrary artificial neural networks (ANNs) using the flexibility of the PyTorch framework. Analog tiles can be conveniently configured to emulate a plethora of different analog hardware characteristics and their non-idealities, such as device-to-device and cycle-to-cycle variations, resistive device response curves, and weight and output noise. Additionally, the toolkit makes it possible to design custom unit cell configurations and to use advanced analog optimization algorithms such as Tiki-Taka. Moreover, the backward and update behavior can be set to "ideal" to enable hardware-aware training features for chips that target inference acceleration only. To evaluate the inference accuracy of such chips over time, we provide statistical programming noise and drift models calibrated on phase-change memory hardware. Our new toolkit is fully GPU accelerated and can be used to conveniently estimate the impact of material properties and non-idealities of future analog technology on the accuracy for arbitrary ANNs.

User-facing software services are becoming increasingly reliant on remote servers to host Deep Neural Network (DNN) models, which perform inference tasks for the clients. Such services require the client to send input data to the service provider, who processes it using a DNN and returns the output predictions to the client. Due to the rich nature of the inputs such as images and speech, the input often contains more information than what is necessary to perform the primary inference task. Consequently, in addition to the primary inference task, a malicious service provider could infer secondary (sensitive) attributes from the input, compromising the client's privacy. The goal of our work is to improve inference privacy by injecting noise to the input to hide the irrelevant features that are not conducive to the primary classification task. T o this end, we propose Adaptive Noise Injection (ANI), which uses a light-weight DNN on the client-side to inject noise to each input, before transmitting it to the service provider to perform inference. Our key insight is that by customizing the noise to each input, we can achieve state-of-the-art trade-off between utility and privacy (up to 48. 5% degradation in sensitive-task accuracy with 1% degradation in primary accuracy), significantly outperforming existing noise injection schemes. Our method does not require prior knowledge of the sensitive attributes and incurs minimal computational overheads.

The consumer Internet of Things (IoT) have developed in recent years. Mass IoT devices are constructed to build a huge communications network. But these devices are insecure in reality, it means that the communications network are exposed by the attacker. Moreover, the IoT communication network also faces with variety of sudden errors. Therefore, it easily leads to that is vulnerable with the threat of attacker and system failure. The severe situation of IoT communication network motivates the development of new techniques to automatically detect multi-anomaly. In this paper, we propose SS-VTCN, a semi-supervised network for IoT multiple anomaly detection that works well effectively for IoT communication network. SS-VTCN is designed to capture the normal patterns of the IoT traffic data based on the distribution whether it is labeled or not by learning their representations with key techniques such as Variational Autoencoders and Temporal Convolutional Network. This network can use the encode data to predict preliminary result, and reconstruct input data to determine anomalies by the representations. Extensive evaluation experiments based on a benchmark dataset and a real consumer smart home dataset demonstrate that SS-VTCN is more suitable than supervised and unsupervised method with better performance when compared other state-of-art semi-supervised method.

The significance of social media has increased manifold in the past few decades as it helps people from even the most remote corners of the world to stay connected. With the advent of technology, digital media has become more relevant and widely used than ever before and along with this, there has been a resurgence in the circulation of fake news and tweets that demand immediate attention. In this paper, we describe a novel Fake News Detection system that automatically identifies whether a news item is "real" or "fake", as an extension of our work in the CONSTRAINT COVID-19 Fake News Detection in English challenge. We have used an ensemble model consisting of pre-trained models followed by a statistical feature fusion network , along with a novel heuristic algorithm by incorporating various attributes present in news items or tweets like source, username handles, URL domains and authors as statistical feature. Our proposed framework have also quantified reliable predictive uncertainty along with proper class output confidence level for the classification task. We have evaluated our results on the COVID-19 Fake News dataset and FakeNewsNet dataset to show the effectiveness of the proposed algorithm on detecting fake news in short news content as well as in news articles. We obtained a best F1-score of 0.9892 on the COVID-19 dataset, and an F1-score of 0.9073 on the FakeNewsNet dataset.

It is well-known that machine learning models are vulnerable to small but cleverly-designed adversarial perturbations that can cause misclassification. While there has been major progress in designing attacks and defenses for various adversarial settings, many fundamental and theoretical problems are yet to be resolved. In this paper, we consider classification in the presence of $\ell_0$-bounded adversarial perturbations, a.k.a. sparse attacks. This setting is significantly different from other $\ell_p$-adversarial settings, with $p\geq 1$, as the $\ell_0$-ball is non-convex and highly non-smooth. Under the assumption that data is distributed according to the Gaussian mixture model, our goal is to characterize the optimal robust classifier and the corresponding robust classification error as well as a variety of trade-offs between robustness, accuracy, and the adversary's budget. To this end, we develop a novel classification algorithm called FilTrun that has two main modules: Filtration and Truncation. The key idea of our method is to first filter out the non-robust coordinates of the input and then apply a carefully-designed truncated inner product for classification. By analyzing the performance of FilTrun, we derive an upper bound on the optimal robust classification error. We also find a lower bound by designing a specific adversarial strategy that enables us to derive the corresponding robust classifier and its achieved error. For the case that the covariance matrix of the Gaussian mixtures is diagonal, we show that as the input's dimension gets large, the upper and lower bounds converge; i.e. we characterize the asymptotically-optimal robust classifier. Throughout, we discuss several examples that illustrate interesting behaviors such as the existence of a phase transition for adversary's budget determining whether the effect of adversarial perturbation can be fully neutralized.

We provide an entropy bound for the spaces of neural networks with piecewise linear activation functions, such as the ReLU and the absolute value functions. This bound generalizes the known entropy bound for the space of linear functions on $\mathbb{R}^d$ and it depends on the value at the point $(1,1,...,1)$ of the networks obtained by taking the absolute values of all parameters of original networks. Keeping this value together with the depth, width and the parameters of the networks to have logarithmic dependence on $1/\varepsilon$, we $\varepsilon$-approximate functions that are analytic on certain regions of $\mathbb{C}^d$. As a statistical application we derive an oracle inequality for the expected error of the considered penalized deep neural network estimators.