To obtain suitable feature distribution is a difficult task in machine learning, especially for unsupervised learning. In this paper, we propose a novel self-learning local supervision encoding framework based on RBMs, in which the self-learning local supervisions from visible layer are integrated into the contrastive divergence (CD) learning of RBMs to constrict and disperse the distribution of the hidden layer features for clustering tasks. In the framework, we use sigmoid transformation to obtain hidden layer and reconstructed hidden layer features from visible layer and reconstructed visible layer units during sampling procedure. The self-learning local supervisions contain local credible clusters which stem from different unsupervised learning and unanimous voting strategy. They are fused into hidden layer features and reconstructed hidden layer features. For the same local clusters, the hidden features and reconstructed hidden layer features of the framework tend to constrict together. Furthermore, the hidden layer features of different local clusters tend to disperse in the encoding process. Under such framework, we present two instantiation models with the reconstruction of two different visible layers. One is self-learning local supervision GRBM (slsGRBM) model with Gaussian linear visible units and binary hidden units using linear transformation for visible layer reconstruction. The other is self-learning local supervision RBM (slsRBM) model with binary visible and hidden units using sigmoid transformation for visible layer reconstruction.

Many real-world systems studied are governed by complex, nonlinear dynamics. By modeling these dynamics, we can gain insight into how these systems work, make predictions about how they will behave, and develop strategies for controlling them. While there are many methods for modeling nonlinear dynamical systems, existing techniques face a trade off between offering interpretable descriptions and making accurate predictions. Here, we develop a class of models that aims to achieve both simultaneously, smoothly interpolating between simple descriptions and more complex, yet also more accurate models. Our probabilistic model achieves this multi-scale property through a hierarchy of locally linear dynamics that jointly approximate global nonlinear dynamics. We call it the tree-structured recurrent switching linear dynamical system. To fit this model, we present a fully-Bayesian sampling procedure using Polya-Gamma data augmentation to allow for fast and conjugate Gibbs sampling. Through a variety of synthetic and real examples, we show how these models outperform existing methods in both interpretability and predictive capability.

We propose self-guided belief propagation (SBP) that modifies belief propagation (BP) by incorporating the pairwise potentials only gradually. This homotopy continuation method converges to a unique solution and increases the accuracy without increasing the computational burden. We apply SBP to grid graphs, complete graphs, and random graphs with random Ising potentials and show that: (i) SBP is superior in terms of accuracy whenever BP converges, and (ii) SBP obtains a unique, stable, and accurate solution whenever BP does not converge. We further provide a formal analysis to demonstrate that SBP obtains the global optimum of the Bethe approximation for attractive models with unidirectional fields.

FRAME (Filters, Random fields, And Maximum Entropy) is an energy-based descriptive model that synthesizes visual realism by capturing mutual patterns from structural input signals. The maximum likelihood estimation (MLE) is applied by default, yet conventionally causes the unstable training energy that wrecks the generated structures, which remains unexplained. In this paper, we provide a new theoretical insight to analyze FRAME, from a perspective of particle physics ascribing the weird phenomenon to KL-vanishing issue. In order to stabilize the energy dissipation, we propose an alternative Wasserstein distance in discrete time based on the conclusion that the Jordan-Kinderlehrer-Otto (JKO) discrete flow approximates KL discrete flow when the time step size tends to 0. Besides, this metric can still maintain the model's statistical consistency. Quantitative and qualitative experiments have been respectively conducted on several widely used datasets. The empirical studies have evidenced the effectiveness and superiority of our method.

We introduce a genetic algorithm that designs quantum optics experiments for engineering quantum states with specific properties. Our algorithm is powerful and flexible, and can easily be modified to find methods of engineering states for a range of applications. Here we focus on quantum metrology. First, we consider the noise-free case, and use the algorithm to find quantum states with a large quantum Fisher information (QFI). We find methods, which only involve experimental elements that are available with current technology, for engineering quantum states with up to a 100-fold improvement over the best classical state, and a 20-fold improvement over the optimal Gaussian state. Such states are a superposition of the vacuum with a large number of photons (around 80), and can hence be seen as Schr\"odinger-cat-like states. We then apply the two most dominant noise sources in our setting -- photon loss and imperfect heralding -- and use the algorithm to find quantum states that still improve over the optimal Gaussian state with realistic levels of noise. This will open up experimental and technological work in using exotic non-Gaussian states for quantum-enhanced phase measurements. Finally, we use the Bayesian mean square error to look beyond the regime of validity of the QFI, finding quantum states with precision enhancements over the alternatives even when the experiment operates in the regime of limited data.

The ability for autonomous agents to learn and conform to human norms is crucial for their safety and effectiveness in social environments. While recent work has led to frameworks for the representation and inference of simple social rules, research into norm learning remains at an exploratory stage. Here, we present a robotic system capable of representing, learning, and inferring ownership relations and norms. Ownership is represented as a graph of probabilistic relations between objects and their owners, along with a database of predicate-based norms that constrain the actions permissible on owned objects. To learn these norms and relations, our system integrates (i) a novel incremental norm learning algorithm capable of both one-shot learning and induction from specific examples, (ii) Bayesian inference of ownership relations in response to apparent rule violations, and (iii) percept-based prediction of an object's likely owners. Through a series of simulated and real-world experiments, we demonstrate the competence and flexibility of the system in performing object manipulation tasks that require a variety of norms to be followed, laying the groundwork for future research into the acquisition and application of social norms.

Recently, compression and acceleration of deep neural networks are in critic need. Bayesian generalization of structured pruning represents an important research direction to solve the above problem. However, the existing Bayesian methods ignore the dependency among neurons and filters for computational simplicity. In this study, we explore, under Bayesian framework, a structured pruning method with layer-wise sequential dependency assumed, a more general learning setting. Based on the property of Dirac distribution, we further derive a new dropout noise, which makes it possible to approximate the posterior of dropout noise knowing that of the previous layer. With the Dirac-like dropout noise, we further propose a recursive strategy, named \emph{Recursive Bayesian Pruning} (RBP), to train and prune networks in a layer-by-layer fashion. The unimportant neurons and filters are directly targeted and removed, taking the influence from the previous layer. Experiments on typical neural networks LeNet-300-100, LeNet-5 and VGG-16 have demonstrated the proposed method are competitive with or even outperform the state-of-the-art methods in several compression and acceleration metrics.

Labeling training data is one of the most costly bottlenecks in developing or modifying machine learning-based applications. We survey how resources from across an organization can be used as weak supervision sources for three classification tasks at Google, in order to bring development time and cost down by an order of magnitude. We build on the Snorkel framework, extending it as a new system, Snorkel DryBell, which integrates with Google's distributed production systems and enables engineers to develop and execute weak supervision strategies over millions of examples in less than thirty minutes. We find that Snorkel DryBell creates classifiers of comparable quality to ones trained using up to tens of thousands of hand-labeled examples, in part by leveraging organizational resources not servable in production which contribute an average 52% performance improvement to the weakly supervised classifiers.

The ability to learn and act in novel situations is still a prerogative of animate intelligence, as current machine learning methods mostly fail when moving beyond the standard i.i.d. setting. What is the reason for this discrepancy? Most machine learning tasks are anti-causal, i.e., we infer causes (labels) from effects (observations). Typically, in supervised learning we build systems that try to directly invert causal mechanisms. Instead, in this paper we argue that strong generalization capabilities crucially hinge on searching and validating meaningful hypotheses, requiring access to a causal model. In such a framework, we want to find a cause that leads to the observed effect. Anti-causal models are used to drive this search, but a causal model is required for validation. We investigate the fundamental differences between causal and anti-causal tasks, discuss implications for topics ranging from adversarial attacks to disentangling factors of variation, and provide extensive evidence from the literature to substantiate our view. We advocate for incorporating causal models in supervised learning to shift the paradigm from inference only, to search and validation.

Early detection of Alzheimer's disease (AD) and identification of potential risk/beneficial factors are important for planning and administering timely interventions or preventive measures. In this paper, we learn a disease model for AD that combines genotypic and phenotypic profiles, and cognitive health metrics of patients. We propose a probabilistic generative subspace that describes the correlative, complementary and domain-specific semantics of the dependencies in multi-view, multi-modality medical data. Guided by domain knowledge and using the latent consensus between abstractions of multi-view data, we model the fusion as a data generating process. We show that our approach can potentially lead to i) explainable clinical predictions and ii) improved AD diagnoses.