The field of few-shot learning has recently seen substantial advancements. Most of these advancements came from casting few-shot learning as a meta-learning problem. Model Agnostic Meta Learning or MAML is currently one of the best approaches for few-shot learning via meta-learning. MAML is simple, elegant and very powerful, however, it has a variety of issues, such as being very sensitive to neural network architectures, often leading to instability during training, requiring arduous hyperparameter searches to stabilize training and achieve high generalization and being very computationally expensive at both training and inference times. In this paper, we propose various modifications to MAML that not only stabilize the system, but also substantially improve the generalization performance, convergence speed and computational overhead of MAML, which we call MAML . The human capacity to learn new concepts using only a handful of samples is immense. In stark contrast, modern deep neural networks need, at a minimum, thousands of samples before they begin to learn representations that can generalize well to unseen data-points (Krizhevsky et al., 2012; Huang et al., 2017), and mostly fail when the data available is scarce. The fact that standard deep neural networks fail in the small data regime can provide hints about some of their potential shortcomings. Solving those shortcomings has the potential to open the door to understanding intelligence and advancing Artificial Intelligence. Few-shot learning encapsulates a family of methods that can learn new concepts with only a handful of data-points (usually 1-5 samples per concept).

Adversarial machine learning is a fast growing research area, which considers the scenarios when machine learning systems may face potential adversarial attackers, who intentionally synthesize input data to make a well-trained model to make mistake. It always involves a defending side, usually a classifier, and an attacking side that aims to cause incorrect output. The earliest studies on the adversarial examples for machine learning algorithms start from the information security area, which considers a much wider varieties of attacking methods. But recent research focus that popularized by the deep learning community places strong emphasis on how the "imperceivable" perturbations on the normal inputs may cause dramatic mistakes by the deep learning with supposed super-human accuracy. This paper serves to give a comprehensive introduction to a range of aspects of the adversarial deep learning topic, including its foundations, typical attacking and defending strategies, and some extended studies.

In online learning, the dynamic regret metric chooses the reference (optimal) solution that may change over time, while the typical (static) regret metric assumes the reference solution to be constant over the whole time horizon. The dynamic regret metric is particularly interesting for applications such as online recommendation (since the customers' preference always evolves over time). While the online gradient method has been shown to be optimal for the static regret metric, the optimal algorithm for the dynamic regret remains unknown. In this paper, we show that proximal online gradient (a general version of online gradient) is optimum to the dynamic regret by showing that the proved lower bound matches the upper bound that slightly improves existing upper bound.

Since Klaus Schwab drew attention to the arrival of the 4th Industrial Revolution in January 2016, we are witnessing the significant impact of Artificial Intelligence and its more well known subset, often seen as its synonym of Machine Learning that led Andrew Ng to propound " AI is the new electricity". India created the IITs in the 1960s that helped some Indians to achieve places of eminence in the technical and business world of the 3rd Industrial Age. Today, India is a ' KRANTI' nation poised to play center-stage in the AI age leveraging the opportunity as a ' learning movement' amongst its masses, evidenced by the rapid adoption of the mobile phone. A group of former IIT faculty and students led by Prof. M.M. Pant have started a movement of AI awareness and lifelong learning to spread knowledge about AI as per one's need. Their Mission 2020 is to prepare not only the young but all ages for their future in the 4th Industrial Age.

It has been always difficult to consume TensorFlow or ONNX models without the help of tools like TensorFlow Serving or gRPC and all the fun that comes with protocol buffers. Hosting deep learning models to be consumed using REST was very hard although this is probably the most common approach application developers would start with. Microsoft has recently released Azure Machine Learning service which comes with heaps of features to facilitate development and deployment of machine learning models. One of those features is hosting ONNX models in docker containers to be consumed using REST. In this post, we go through an end to end workflow of hosting a sample ONNX model and consuming it from a .NET application.

In spite of the fact that the idea of Artificial Intelligence has been around for a long time, it is just in the most recent years that it has gotten on the tech charts and is trending in each and every industry conceivable. Getting to be noticeably extraordinary compared to other cherished techs among the ingenious minds all over the world, Artificial Intelligence demands a mix of computer science, mathematics, cognitive psychology, and engineering. There is no doubt about that soon the demand for experts prepared in Artificial Intelligence would beat supply. In spite of the fact that there is some overlap of Artificial Intelligence with analytics, a capable Artificial Intelligence expert would have profound knowledge on spheres like computer vision, natural language processing, robotics automation, and machine learning. Artificial Intelligence education is still in its youthful days.

Once upon a time if I wanted to find my way to somewhere unfamiliar, I would have pulled out a map and plotted my route. These days I just put the destination into my smartphone and let it make all the decisions. Is this a simple, practical thing to do or, by relying on increasingly smarter phones, are we allowing them to make us, day by day, a little bit dumber? I've spent the last few days at an international conference on artificial intelligence pondering just this question. We were discussing, among other things, the effect that the rise of machine intelligence is having on our brains.

The learning problem in machine intelligence has been traditionally formulated as an optimization task where an error metric is minimized. In the system of linear equations, becauseit is difficulttohave anexact match between thesamplesizeand the number of model parameters, an approximation is often sought-after according to the primal solution space or the dual solution space in the least error sense. Such an optimization, particularly one that is based on minimizing the least squares error, has been a popular choice due to its simplicity and tractability in analysis and implementation. The approach is predominant in engineering applications as evident from its pervasive adoption in statistical and network learning. Attributed to the computational effectiveness of the backpropagation algorithm running on the then limited hardware (see e.g.,[1, 2, 3, 4, 5]) and the theoretical establishment of the mapping capability (see e.g., [6, 7, 8, 9]), the multilayer neural networks were once a popular tool for research and applications in the 1980s.

Classification methods based on sparse estimation have drawn much attention recently, due to their effectiveness in processing high-dimensional data such as images. In this paper, a method to improve the performance of a sparse representation classification (SRC) approach is proposed; it is then applied to the problem of online process monitoring of human workers, specifically manual material handling (MMH) operations monitored using wearable sensors (involving 111 sensor channels). Our proposed method optimizes the design matrix (aka dictionary) in the linear model used for SRC, minimizing its ill-posedness to achieve a sparse solution. This procedure is based on the idea of dictionary learning (DL): we optimize the design matrix formed by training datasets to minimize both redundancy and coherency as well as reducing the size of these datasets. Use of such optimized training data can subsequently improve classification accuracy and help decrease the computational time needed for the SRC; it is thus more applicable for online process monitoring. Performance of the proposed methodology is demonstrated using wearable sensor data obtained from manual material handling experiments, and is found to be superior to those of benchmark methods in terms of accuracy, while also requiring computational time appropriate for MMH online monitoring.

During the last decade, a considerable amount of effort has been made to classify variable stars using different machine learning techniques. Typically, light curves are represented as vectors of statistical descriptors or features that are used to train various algorithms. These features demand big computational powers that can last from hours to days, making impossible to create scalable and efficient ways of automatically classifying variable stars. Also, light curves from different surveys cannot be integrated and analyzed together when using features, because of observational differences. For example, having variations in cadence and filters, feature distributions become biased and require expensive data-calibration models. The vast amount of data that will be generated soon make necessary to develop scalable machine learning architectures without expensive integration techniques. Convolutional Neural Networks have shown impressing results in raw image classification and representation within the machine learning literature. In this work, we present a novel Deep Learning model for light curve classification, mainly based on convolutional units. Our architecture receives as input the differences between time and magnitude of light curves. It captures the essential classification patterns regardless of cadence and filter. In addition, we introduce a novel data augmentation schema for unevenly sampled time series. We test our method using three different surveys: OGLE-III; Corot; and VVV, which differ in filters, cadence, and area of the sky. We show that besides the benefit of scalability, our model obtains state of the art levels accuracy in light curve classification benchmarks.