Principal component analysis (PCA) and independent component analysis (ICA) are widely used to generate functional brain networks. Moreover, dictionary learning and sparse representation provide some latent patterns that rules brain activities and they can be interpreted as brain networks. However, these methods lack modeling dependencies of the discovered networks. In this study an alternative to these conventional methods is presented in which dependencies of the networks are considered via correlated sparsity patterns. We formulate this challenge as a new dictionary learning problem and propose two approaches to solve the problem effectively.

Abstract: Nonlinear independent component analysis (nICA) aims at recovering statistically independent latent components that are mixed by unknown nonlinear functions. Central to nICA is the identifiability of the latent components, which had been elusive until very recently. Specifically, Hyvärinen et al. have shown that the nonlinearly mixed latent components are identifiable (up to often inconsequential ambiguities) under a generalized contrastive learning (GCL) formulation, given that the latent components are independent conditioned on a certain auxiliary variable. The GCL-based identifiability of nICA is elegant, and establishes interesting connections between nICA and popular unsupervised/self-supervised learning paradigms in representation learning, causal learning, and factor disentanglement. However, existing identifiability analyses of nICA all build upon an unlimited sample assumption and the use of ideal universal function learners -- which creates a non-negligible gap between theory and practice.

There are 4 mathematical pre-requisite (or let's call them "essentials") for Data Science/Machine Learning/Deep Learning, namely: In fact, behind every Machine Learning (and Deep Learning) algorithm, some optimization is involved. Ok, let me take the simplest possible example. Everyone familiar with machine learning will immediately recognize that we are referring to X1 as the independent variable (also called "Features" or "Attributes"), and the Y is the dependent variable (also referred to as the "Target" or "Outcome"). Hence, the overall task of any machine is to find the relationship between X1 & Y. This relationship is actually "learned" by the machine from the DATA, and hence we call the term Machine Learning.

Originally published on Towards AI the World's Leading AI and Technology News and Media Company. If you are building an AI-related product or service, we invite you to consider becoming an AI sponsor. At Towards AI, we help scale AI and technology startups. Let us help you unleash your technology to the masses. Most deep learning algorithms train by optimizing some kind of objective (or loss) function. We typically try to either maximize or minimize these functions.

The Predictive Airliner is an airline that utilizes the latest technology to deliver an exceptional personalized experience to each and every passenger it flies. Today, technology such as AI, Machine Learning, Augmented Reality, IoT, Real-time stream processing, social media, streaming analytics and wearables are altering the Customer Experience (CX) landscape and airlines need to jump aboard this fast moving technology or run the risk of being left out in the cold. The Predictive Airliner reveals how these and other technologies can help shape the customer journey. The book details how the five types of analytics--descriptive, diagnostic, predictive, prescriptive, and edge analytics--affect not only the customer journey, but also just about every operational function within an airline. An IoT-connected airline can make its operations smart.

The k-nearest neighbors (kNN) algorithm is a simple tool that can be used for a number of real-world problems in finance, healthcare, recommendation systems, and much more. This blog post will cover what kNN is, how it works, and how to implement it in machine learning projects. The k-nearest neighbors classifier (kNN) is a non-parametric supervised machine learning algorithm. It's distance-based: it classifies objects based on their proximate neighbors' classes. What is a supervised machine learning model?

Knowledge distillation is a popular machine learning technique that aims to transfer knowledge from a large 'teacher' network to a smaller 'student' network and improve the student's performance by training it to emulate the teacher. In recent years, there has been significant progress in novel distillation techniques that push performance frontiers across multiple problems and benchmarks. Most of the reported work focuses on achieving state-of-the-art results on the specific problem. However, there has been a significant gap in understanding the process and how it behaves under certain training scenarios. Similarly, transfer learning (TL) is an effective technique in training neural networks on a limited dataset faster by reusing representations learned from a different but related problem. Despite its effectiveness and popularity, there has not been much exploration of knowledge distillation on transfer learning. In this thesis, we propose a machine learning architecture we call TL+KD that combines knowledge distillation with transfer learning; we then present a quantitative and qualitative comparison of TL+KD with TL in the domain of image classification. Through this work, we show that using guidance and knowledge from a larger teacher network during fine-tuning, we can improve the student network to achieve better validation performances like accuracy. We characterize the improvement in the validation performance of the model using a variety of metrics beyond just accuracy scores, and study its performance in scenarios such as input degradation.

Optimizing expensive-to-evaluate black-box functions of discrete (and potentially continuous) design parameters is a ubiquitous problem in scientific and engineering applications. Bayesian optimization (BO) is a popular, sample-efficient method that leverages a probabilistic surrogate model and an acquisition function (AF) to select promising designs to evaluate. However, maximizing the AF over mixed or high-cardinality discrete search spaces is challenging standard gradient-based methods cannot be used directly or evaluating the AF at every point in the search space would be computationally prohibitive. To address this issue, we propose using probabilistic reparameterization (PR). Instead of directly optimizing the AF over the search space containing discrete parameters, we instead maximize the expectation of the AF over a probability distribution defined by continuous parameters. We prove that under suitable reparameterizations, the BO policy that maximizes the probabilistic objective is the same as that which maximizes the AF, and therefore, PR enjoys the same regret bounds as the original BO policy using the underlying AF. Moreover, our approach provably converges to a stationary point of the probabilistic objective under gradient ascent using scalable, unbiased estimators of both the probabilistic objective and its gradient. Therefore, as the number of starting points and gradient steps increase, our approach will recover of a maximizer of the AF (an often-neglected requisite for commonly used BO regret bounds). We validate our approach empirically and demonstrate state-of-the-art optimization performance on a wide range of real-world applications. PR is complementary to (and benefits) recent work and naturally generalizes to settings with multiple objectives and black-box constraints.

We explore using neural operators, or neural network representations of nonlinear maps between function spaces, to accelerate infinite-dimensional Bayesian inverse problems (BIPs) with models governed by nonlinear parametric partial differential equations (PDEs). Neural operators have gained significant attention in recent years for their ability to approximate the parameter-to-solution maps defined by PDEs using as training data solutions of PDEs at a limited number of parameter samples. The computational cost of BIPs can be drastically reduced if the large number of PDE solves required for posterior characterization are replaced with evaluations of trained neural operators. However, reducing error in the resulting BIP solutions via reducing the approximation error of the neural operators in training can be challenging and unreliable. We provide an a priori error bound result that implies certain BIPs can be ill-conditioned to the approximation error of neural operators, thus leading to inaccessible accuracy requirements in training. To reliably deploy neural operators in BIPs, we consider a strategy for enhancing the performance of neural operators, which is to correct the prediction of a trained neural operator by solving a linear variational problem based on the PDE residual. We show that a trained neural operator with error correction can achieve a quadratic reduction of its approximation error, all while retaining substantial computational speedups of posterior sampling when models are governed by highly nonlinear PDEs. The strategy is applied to two numerical examples of BIPs based on a nonlinear reaction--diffusion problem and deformation of hyperelastic materials. We demonstrate that posterior representations of the two BIPs produced using trained neural operators are greatly and consistently enhanced by error correction.

Variance-reduced stochastic gradient methods have gained popularity in recent times. Several variants exist with different strategies for the storing and sampling of gradients and this work concerns the interactions between these two aspects. We present a general proximal variance-reduced gradient method and analyze it under strong convexity assumptions. Special cases of the algorithm include SAGA, L-SVRG and their proximal variants. Our analysis sheds light on epoch-length selection and the need to balance the convergence of the iterates with how often gradients are stored. The analysis improves on other convergence rates found in the literature and produces a new and faster converging sampling strategy for SAGA. Problem instances for which the predicted rates are the same as the practical rates are presented together with problems based on real world data.