We present an approach to cosmology in which the Universe learns its own physical laws. It does so by exploring a landscape of possible laws, which we express as a certain class of matrix models. We discover maps that put each of these matrix models in correspondence with both a gauge/gravity theory and a mathematical model of a learning machine, such as a deep recurrent, cyclic neural network. This establishes a correspondence between each solution of the physical theory and a run of a neural network. This correspondence is not an equivalence, partly because gauge theories emerge from $N \rightarrow \infty $ limits of the matrix models, whereas the same limits of the neural networks used here are not well-defined. We discuss in detail what it means to say that learning takes place in autodidactic systems, where there is no supervision. We propose that if the neural network model can be said to learn without supervision, the same can be said for the corresponding physical theory. We consider other protocols for autodidactic physical systems, such as optimization of graph variety, subset-replication using self-attention and look-ahead, geometrogenesis guided by reinforcement learning, structural learning using renormalization group techniques, and extensions. These protocols together provide a number of directions in which to explore the origin of physical laws based on putting machine learning architectures in correspondence with physical theories.

Can deep learning solve multiple tasks simultaneously, even when they are unrelated and very different? We investigate how the representations of the underlying tasks affect the ability of a single neural network to learn them jointly. We present theoretical and empirical findings that a single neural network is capable of simultaneously learning multiple tasks from a combined data set, for a variety of methods for representing tasks--for example, when the distinct tasks are encoded by well-separated clusters or decision trees over certain task-code attributes. More concretely, we present a novel analysis that shows that families of simple programming-like constructs for the codes encoding the tasks are learnable by two-layer neural networks with standard training. We study more generally how the complexity of learning such combined tasks grows with the complexity of the task codes; we find that combining many tasks may incur a sample complexity penalty, even though the individual tasks are easy to learn. We provide empirical support for the usefulness of the learning bounds by training networks on clusters, decision trees, and SQL-style aggregation. Standard practice in machine learning has long been to only address carefully circumscribed, often very related tasks. For example, we might train a single classifier to label an image as containing objects from a certain predefined set, or to label the words of a sentence with their semantic roles. Indeed, when working with relatively simple classes of functions like linear classifiers, it would be unreasonable to expect to train a classifier that handles more than such a carefully scoped task (or related tasks in standard multitask learning). As techniques for learning with relatively rich classes such as neural networks have been developed, it is natural to ask whether or not such scoping of tasks is inherently necessary. Indeed, many recent works (see Section 1.2) have proposed eschewing this careful scoping of tasks, and instead training a single, "monolithic" function spanning many tasks. Large, deep neural networks can, in principle, represent multiple classifiers in such a monolithic learned function (Hornik, 1991), giving rise to the field of multitask learning. This combined function might be learned by combining all of the training data for all of the tasks into one large batch-see Section 1.2 for some examples. Taken to an extreme, we could consider seeking to learn a universal circuit--that is, a circuit that interprets arbitrary programs in a programming language which can encode various tasks. But, the ability to represent such a monolithic combined function does not necessarily entail that such a function can be efficiently learned by existing methods.

ABSTRACT Regional rainfall forecasting is an important issue in hydrology and meteorology. This paper aims to design an integrated tool by applying various machine learning algorithms, especially the state-of-the-art deep learning algorithms including Deep Neural Network, Wide Neural Network, Deep and Wide Neural Network, Reservoir Computing, Long Short Term Memory, Support Vector Machine, K-Nearest Neighbor for forecasting regional precipitations over different catchments in Upstate New York. Through the experimental results and the comparison among machine learning models including classification and regression, we find that KNN is an outstanding model over other models to handle the uncertainty in the precipitation data. The data normalization methods such as ZScore and MinMax are also evaluated and discussed. Keywords: rainfall forecasting, k-nearest neighbor, deep and wide neural network, reservoir computing, long short term memory. 1 INTRODUCTION New York historically had sufficient precipitation until recently, with intense drought occurring over the 2016 growing season, especially in western New York (Todaro 2018). The observed precipitation in 2016 was less than normal, with shortfalls of 4-8 inches being common in the 90 days leading up to the drought watch. Accurate rainfall forecasting is important for planning in agriculture and other relevant activities. Although a number of modern algorithms and applications have been used to forecast rainfall, there are two categories of approaches to solve the problem. However, it is thought not feasible limited by the complex climatic system in various spatial and temporal dimensions. A second category is based on the data mining and pattern recognition, which attempts to mine rainfall patterns and learn the knowledge from numerous features and a large volume of data. Historical meteorological data including precipitation data are used to feed and train the recognition model and further predict the evolution of other storms.

Online information systems currently heavily rely on the username and password traditional method for protecting information and controlling access. With the advancement in biometric technology and popularity of fields like AI and Machine Learning, biometric security is becoming increasingly popular because of the usability advantage. This paper reports how machine learning based face recognition can be integrated into a web-based system as a method of authentication to reap the benefits of improved usability. This paper includes a comparison of combinations of detection and classification algorithms with FaceNet for face recognition. The results show that a combination of MTCNN for detection, Facenet for generating embeddings, and LinearSVC for classification outperforms other combinations with a 95% accuracy. The resulting classifier is integrated into the web-based system and used for authenticating users.

At present, SOILD-STATE Fermentation (SSF) is mainly controlled by artificial experience, and the product quality and yield are not stable. Accurately predicting the quality and yield of SSF is of great significance for improving human food security and supply. In this paper, we propose an Intelligent Utility Prediction (IUP) scheme for SSF in 5G Industrial Internet of Things (IoT), including parameter collection and utility prediction of SSF process. This IUP scheme is based on the environmental perception and intelligent learning algorithms of the 5G Industrial IoT. We build a workflow model based on rewritable petri net to verify the correctness of the system model function and process. In addition, we design a utility prediction model for SSF based on the Generative Adversarial Networks (GAN) and Fully Connected Neural Network (FCNN). We design a GAN with constraint of mean square error (MSE-GAN) to solve the problem of few-shot learning of SSF, and then combine with the FCNN to realize the utility prediction (usually use the alcohol) of SSF. Based on the production of liquor in laboratory, the experiments show that the proposed method is more accurate than the other prediction methods in the utility prediction of SSF, and provide the basis for the numerical analysis of the proportion of preconfigured raw materials and the appropriate setting of cellar temperature.

Video-Text Retrieval has been a hot research topic with the explosion of multimedia data on the Internet. Transformer for video-text learning has attracted increasing attention due to the promising performance.However, existing cross-modal transformer approaches typically suffer from two major limitations: 1) Limited exploitation of the transformer architecture where different layers have different feature characteristics. 2) End-to-end training mechanism limits negative interactions among samples in a mini-batch. In this paper, we propose a novel approach named Hierarchical Transformer (HiT) for video-text retrieval. HiT performs hierarchical cross-modal contrastive matching in feature-level and semantic-level to achieve multi-view and comprehensive retrieval results. Moreover, inspired by MoCo, we propose Momentum Cross-modal Contrast for cross-modal learning to enable large-scale negative interactions on-the-fly, which contributes to the generation of more precise and discriminative representations. Experimental results on three major Video-Text Retrieval benchmark datasets demonstrate the advantages of our methods.

For some reason, data exploration and cleaning are often seen as the lesser-arts of the data science world. This could not be more wrong. EDA is the only way for data scientists to really get a grasp on the problem. Exploring the data is crucial for understanding what the data really represents; rather than what we might think it represents. Indeed data often includes biases (e.g. are the label's representative of the class they are supposed to define?

GPT-3 also known as Generative Pre-Trained Transformer 3 is an advanced autoregressive language model that uses deep learning to produce human-like text. A recent experience by the medical Paris-based firm, Nabla, specialising in healthcare technology used a cloud-hosted instance of GPT-3 to analyse queries by humans and produce a suitable answer to them. The bot was designed to ease the daily workload of doctors however the unpredictable nature of the software's responses made it inappropriate for interacting with patients in the real world; this was concluded after running a series of tests.

With the advent of deep learning, implementing an object detection system has become fairly trivial. There are a great many frameworks facilitating the process, and as I showed in a previous post, it's quite easy to create a fast object detection model with YOLOv5. However, understanding the basics of object detection is still quite difficult. It involves a lot of math, and the variable number of outputs/bounding boxes makes it harder to understand than image classification, where we know the number of outputs beforehand. With so many moving parts and new concepts introduced over the history of object detection, it certainly hasn't gotten easier. In this post, I'll distill all this history into a simple guide that explains all the details of object detection and instance segmentation systems. The classic image classification problem is very well known: given an image, can you find the class the image belongs to? We can solve any new image classification problem with ConvNets and transfer learning using pre-trained nets where Convnets are fixed feature extractors.

With continued advances in science and technology, digital data have grown at an astonishing rate in various domains and forms, such as business, geography, health, multimedia, network, text, and web data. Machine learning, a powerful tool for automatically extracting, managing, inferencing, and transferring knowledge, has been proven to be extremely useful in understanding the intrinsic nature of real-world big data. Despite achieving remarkable performance, machine learning models, especially deep learning models, suffer from harassment caused by small adversarial perturbations injected by malicious parties and users. There is an immediate and crucial need for theoretical and practical techniques to identify the vulnerability of machine learning models and explore the defense mechanism and the certifiable robustness.The goal of this Research Topic is to present state-of-the-art methodologies build upon an innovative blend of techniques from computer science, mathematics, and statistics, and to greatly expand the reach of adversarial machine learning from both theoretical and practical points of view, allowing the machine learning models to be deployed in safety and security-critical applications. This Research Topic will focus on three main research tasks: (1) How to develop effective modification 'attack' strategies to tamper with intrinsic characteristics of data by injecting fake information? (2) How to develop defense strategies to offer sufficient protection to mach...