Collaborating Authors


A Brief Introduction to Fundamentals of Machine Learning


Data adventure, which started with data mining concept, has been in a continuous development with introducing different algorithms. There are many applicable algorithms in AI. Besides, AI is actively used in marketing, health, agriculture, space, and autonomous vehicle production for now. Data mining is divided into different models according to fields in which it is used. These models can be grouped under four main headings as a value estimation model, database clustering model, link analysis, and difference deviations.

Unsupervised Machine Learning From First Principles


Attribution for the core content is given to the textbook "Hands-On Unsupervised Learning Using Python: How to Build Applied Machine Learning Solutions from Unlabeled Data" which I would urge you to buy on Amazon

Using Unsupervised Learning to Combat Cyber Threats


As the world enters a fully digital age, cyber threats are on the rise with massive data breaches, hacks into personal and financial data, and any other digital source that people can exploit. To combat these attacks, security experts are increasingly tapping into AI to stay a step ahead using every tool in their toolbox including unsupervised learning methods. Machine learning in the cybersecurity space is considered to still be in its infancy stage, but there has been a lot of traction since 2020 to have more AI involved in the process of combating cyber threats. Understanding how machine learning can be used in cyber security, recognizing the need for unsupervised learning methods in cyber security, and knowing how to implement AI in combating cyber attacks are the key to fighting cybercrime in the years ahead. The scary thing about cybercrime is that it can take up to six months to even detect a breach, and it takes an average of roughly 50 days from the time a breach is found to the time it is reported.

What are the types of machine learning?


At a high-level, machine learning is simply the study of teaching a computer program or algorithm how to progressively improve upon a set task that it is given. On the research-side of things, machine learning can be viewed through the lens of theoretical and mathematical modeling of how this process works. However, more practically it is the study of how to build applications that exhibit this iterative improvement. There are many ways to frame this idea, but largely there are three major recognized categories: supervised learning, unsupervised learning, and reinforcement learning. In a world saturated by artificial intelligence, machine learning, and over-zealous talk about both, it is interesting to learn to understand and identify the types of machine learning we may encounter.

A survey of unsupervised learning methods for high-dimensional uncertainty quantification in black-box-type problems Machine Learning

Constructing surrogate models for uncertainty quantification (UQ) on complex partial differential equations (PDEs) having inherently high-dimensional $\mathcal{O}(10^{\ge 2})$ stochastic inputs (e.g., forcing terms, boundary conditions, initial conditions) poses tremendous challenges. The curse of dimensionality can be addressed with suitable unsupervised learning techniques used as a pre-processing tool to encode inputs onto lower-dimensional subspaces while retaining its structural information and meaningful properties. In this work, we review and investigate thirteen dimension reduction methods including linear and nonlinear, spectral, blind source separation, convex and non-convex methods and utilize the resulting embeddings to construct a mapping to quantities of interest via polynomial chaos expansions (PCE). We refer to the general proposed approach as manifold PCE (m-PCE), where manifold corresponds to the latent space resulting from any of the studied dimension reduction methods. To investigate the capabilities and limitations of these methods we conduct numerical tests for three physics-based systems (treated as black-boxes) having high-dimensional stochastic inputs of varying complexity modeled as both Gaussian and non-Gaussian random fields to investigate the effect of the intrinsic dimensionality of input data. We demonstrate both the advantages and limitations of the unsupervised learning methods and we conclude that a suitable m-PCE model provides a cost-effective approach compared to alternative algorithms proposed in the literature, including recently proposed expensive deep neural network-based surrogates and can be readily applied for high-dimensional UQ in stochastic PDEs.

Data Annotation for Machine Learning: A to Z Guide


Machine learning is embedded in AI and allows machines to perform specific tasks through training. With data annotation, it can learn about pretty much everything. Supervised Learning: The supervised learning learns from a set of labeled data. It is an algorithm that predicts the outcome of new data based on previously known labeled data. Unsupervised Learning: In unsupervised machine learning, training is based on unlabeled data. In this algorithm, you don't know the outcome or the label of the input data.

How to Leverage Unlabeled Data in Offline Reinforcement Learning Artificial Intelligence

Offline reinforcement learning (RL) can learn control policies from static datasets but, like standard RL methods, it requires reward annotations for every transition. In many cases, labeling large datasets with rewards may be costly, especially if those rewards must be provided by human labelers, while collecting diverse unlabeled data might be comparatively inexpensive. How can we best leverage such unlabeled data in offline RL? One natural solution is to learn a reward function from the labeled data and use it to label the unlabeled data. In this paper, we find that, perhaps surprisingly, a much simpler method that simply applies zero rewards to unlabeled data leads to effective data sharing both in theory and in practice, without learning any reward model at all. While this approach might seem strange (and incorrect) at first, we provide extensive theoretical and empirical analysis that illustrates how it trades off reward bias, sample complexity and distributional shift, often leading to good results. We characterize conditions under which this simple strategy is effective, and further show that extending it with a simple reweighting approach can further alleviate the bias introduced by using incorrect reward labels. Our empirical evaluation confirms these findings in simulated robotic locomotion, navigation, and manipulation settings.

Netacea's approach to machine learning: unsupervised and supervised models


Our world is driven by technological innovation. Recent years have seen many companies adopt artificial intelligence (AI) and machine learning technology to analyze larger data sets and perform more complex tasks with faster and more accurate results. This is not limited to technology-based industries such as computer science -- now, many industries work continuously to enhance their technology to keep up with consumer expectations, with data-based decision making often central to this drive. Designed to imitate the way that humans learn, machine learning technology makes use of data and algorithms to gather knowledge and gradually improve accuracy over time. There are many machine learning applications; the two most commonly used and referred to machine learning models are supervised learning and unsupervised learning.

ColloSSL: Collaborative Self-Supervised Learning for Human Activity Recognition Artificial Intelligence

A major bottleneck in training robust Human-Activity Recognition models (HAR) is the need for large-scale labeled sensor datasets. Because labeling large amounts of sensor data is an expensive task, unsupervised and semi-supervised learning techniques have emerged that can learn good features from the data without requiring any labels. In this paper, we extend this line of research and present a novel technique called Collaborative Self-Supervised Learning (ColloSSL) which leverages unlabeled data collected from multiple devices worn by a user to learn high-quality features of the data. A key insight that underpins the design of ColloSSL is that unlabeled sensor datasets simultaneously captured by multiple devices can be viewed as natural transformations of each other, and leveraged to generate a supervisory signal for representation learning. We present three technical innovations to extend conventional self-supervised learning algorithms to a multi-device setting: a Device Selection approach which selects positive and negative devices to enable contrastive learning, a Contrastive Sampling algorithm which samples positive and negative examples in a multi-device setting, and a loss function called Multi-view Contrastive Loss which extends standard contrastive loss to a multi-device setting. Our experimental results on three multi-device datasets show that ColloSSL outperforms both fully-supervised and semi-supervised learning techniques in majority of the experiment settings, resulting in an absolute increase of upto 7.9% in F_1 score compared to the best performing baselines. We also show that ColloSSL outperforms the fully-supervised methods in a low-data regime, by just using one-tenth of the available labeled data in the best case.

Deep Reference Priors: What is the best way to pretrain a model? Machine Learning

What is the best way to exploit extra data -- be it unlabeled data from the same task, or labeled data from a related task -- to learn a given task? This paper formalizes the question using the theory of reference priors. Reference priors are objective, uninformative Bayesian priors that maximize the mutual information between the task and the weights of the model. Such priors enable the task to maximally affect the Bayesian posterior, e.g., reference priors depend upon the number of samples available for learning the task and for very small sample sizes, the prior puts more probability mass on low-complexity models in the hypothesis space. This paper presents the first demonstration of reference priors for medium-scale deep networks and image-based data. We develop generalizations of reference priors and demonstrate applications to two problems. First, by using unlabeled data to compute the reference prior, we develop new Bayesian semi-supervised learning methods that remain effective even with very few samples per class. Second, by using labeled data from the source task to compute the reference prior, we develop a new pretraining method for transfer learning that allows data from the target task to maximally affect the Bayesian posterior. Empirical validation of these methods is conducted on image classification datasets.