Areas under ROC (AUROC) and precision-recall curves (AUPRC) are common metrics for evaluating classification performance for imbalanced problems. Compared with AUROC, AUPRC is a more appropriate metric for highly imbalanced datasets. While direct optimization of AUROC has been studied extensively, optimization of AUPRC has been rarely explored. In this work, we propose a principled technical method to optimize AUPRC for deep learning. Our approach is based on maximizing the averaged precision (AP), which is an unbiased point estimator of AUPRC. We show that the surrogate loss function for AP is highly non-convex and more complicated than that of AUROC. We cast the objective into a sum of dependent compositional functions with inner functions dependent on random variables of the outer level. We propose efficient adaptive and non-adaptive stochastic algorithms with provable convergence guarantee under mild conditions by using recent advances in stochastic compositional optimization. Extensive experimental results on graphs and image datasets demonstrate that our proposed method outperforms prior methods on imbalanced problems. To the best of our knowledge, our work represents the first attempt to optimize AUPRC with provable convergence.

In the midst of all the excitement around Big Data, we keep hearing the term "Machine Learning". It not only offers a lucrative career, but it also promises to solve problems and support businesses by making forecasts and assisting them in making smart decisions. Today, we will learn about the 10 Popular Must-Read Free Machine Learning eBooks in this article. Python Machine Learning is one of the most popular ML books of the last decade. This book is an essential addition to anyone's ML and AI learning plan, as it walks you through the data pipeline step-by-step and shows you how to use the leading machine and Deep Learning libraries, such as scikit-learn and TensorFlow.

Data annotation is the way toward labelling images, audio, video frames, and text information primarily utilized in directed ML to prepare and train the datasets that assist a machine with understanding the input info and act as needs are. There are many kinds of annotations: bounding boxes, landmark annotation, semantic division, polyline annotation, polygon annotation, key issues, named entity recognition, and 3D point cloud annotations. With the headways in deep learning algorithms, NLP and computer vision have extraordinarily developed and done miracles around the world of Artificial Intelligence. Alongside this, AutoML has additionally developed. It has driven numerous enterprises to adopt AI quickly and use it in original use cases.

Deep learning (DL) applications have unique architectural characteristics and efficiency requirements. Hence, the choice of computing system has a profound impact on how large a piece of the DL pie a user can finally enjoy. Even though accelerators may provide higher throughput than general-purpose computing systems (CPUs), there are several other metrics and usage scenarios on which CPUs are preferred or are superior. A recent survey paper I've coauthored with Poonam Rajput and Sreenivas Subramoney (A Survey of Deep Learning on CPUs: Opportunities and Co-optimizations) highlights the strengths of CPUs in DL, and identifies opportunities for further optimization. Sparse DNNs are inefficient on massively parallel processors because of their irregular memory accesses and inability to leverage optimizations such as cache tiling and vectorization.

The idea of artificial general intelligence as we know it today starts with a dot-com blowout on Broadway. Twenty years ago--before Shane Legg clicked with neuroscience postgrad Demis Hassabis over a shared fascination with intelligence; before the pair hooked up with Hassabis's childhood friend Mustafa Suleyman, a progressive activist, to spin that fascination into a company called DeepMind; before Google bought that company for more than half a billion dollars four years later--Legg worked at a startup in New York called Webmind, set up by AI researcher Ben Goertzel. Today the two men represent two very different branches of the future of artificial intelligence, but their roots reach back to common ground. Even for the heady days of the dot-com bubble, Webmind's goals were ambitious. Goertzel wanted to create a digital baby brain and release it onto the internet, where he believed it would grow up to become fully self-aware and far smarter than humans.

Deep learning webinars by Edureka will help you learn various Deep Learning fundamental concepts and popular algorithms like CNN, RCNN, RNN, LSTM, RBM. In these free Deep Learning tutorial series, you will be working on various AI and Deep Learning projects with hands-on.

Whatever business a company may be in, software plays an increasingly vital role, from managing inventory to interfacing with customers. Software developers, as a result, are in greater demand than ever, and that's driving the push to automate some of the easier tasks that take up their time. Productivity tools like Eclipse and Visual Studio suggest snippets of code that developers can easily drop into their work as they write. These automated features are powered by sophisticated language models that have learned to read and write computer code after absorbing thousands of examples. But like other deep learning models trained on big datasets without explicit instructions, language models designed for code-processing have baked-in vulnerabilities.

Recently, CycleGAN was shown to provide high-performance, ultra-fast denoising for low-dose X-ray computed tomography (CT) without the need for a paired training dataset. Although this was possible thanks to cycle consistency, CycleGAN requires two generators and two discriminators to enforce cycle consistency, demanding significant GPU resources and technical skills for training. A recent proposal of tunable CycleGAN with Adaptive Instance Normalization (AdaIN) alleviates the problem in part by using a single generator. However, two discriminators and an additional AdaIN code generator are still required for training. To solve this problem, here we present a novel cycle-free Cycle-GAN architecture, which consists of a single generator and a discriminator but still guarantees cycle consistency. The main innovation comes from the observation that the use of an invertible generator automatically fulfills the cycle consistency condition and eliminates the additional discriminator in the CycleGAN formulation. To make the invertible generator more effective, our network is implemented in the wavelet residual domain. Extensive experiments using various levels of low-dose CT images confirm that our method can significantly improve denoising performance using only 10% of learnable parameters and faster training time compared to the conventional CycleGAN.

Transformer-based pre-trained language models have significantly improved the performance of various natural language processing (NLP) tasks in the recent years. While effective and prevalent, these models are usually prohibitively large for resource-limited deployment scenarios. A thread of research has thus been working on applying network pruning techniques under the pretrain-then-finetune paradigm widely adopted in NLP. However, the existing pruning results on benchmark transformers, such as BERT, are not as remarkable as the pruning results in the literature of convolutional neural networks (CNNs). In particular, common wisdom in pruning CNN states that sparse pruning technique compresses a model more than that obtained by reducing number of channels and layers (Elsen et al., 2020; Zhu and Gupta, 2017), while existing works on sparse pruning of BERT yields inferior results than its small-dense counterparts such as TinyBERT (Jiao et al., 2020). In this work, we aim to fill this gap by studying how knowledge are transferred and lost during the pre-train, fine-tune, and pruning process, and proposing a knowledge-aware sparse pruning process that achieves significantly superior results than existing literature. We show for the first time that sparse pruning compresses a BERT model significantly more than reducing its number of channels and layers. Experiments on multiple data sets of GLUE benchmark show that our method outperforms the leading competitors with a 20-times weight/FLOPs compression and neglectable loss in prediction accuracy.

Finding the best mathematical equation to deal with the different challenges found in complex scenarios requires a thorough understanding of the scenario and a trial and error process carried out by experts. In recent years, most state-of-the-art equation discovery methods have been widely applied in modeling and identification systems. However, equation discovery approaches can be very useful in computer vision, particularly in the field of feature extraction. In this paper, we focus on recent AI advances to present a novel framework for automatically discovering equations from scratch with little human intervention to deal with the different challenges encountered in real-world scenarios. In addition, our proposal can reduce human bias by proposing a search space design through generative network instead of hand-designed. As a proof of concept, the equations discovered by our framework are used to distinguish moving objects from the background in video sequences. Experimental results show the potential of the proposed approach and its effectiveness in discovering the best equation in video sequences.