I-Optimality
The generalized linear model plays an important role in statistical analysis and the related design issues are undoubtedly challenging. The state-of-the-art works mostly apply to design criteria on the estimates of regression coefficients. It is of importance to study optimal designs for generalized linear models, especially on the prediction aspects. In this work, we propose a prediction-oriented design criterion, I-optimality, and develop an efficient sequential algorithm of constructing I-optimal designs for generalized linear models. Through establishing the General Equivalence Theorem of the I-optimality for generalized linear models, we obtain an insightful understanding for the proposed algorithm on how to sequentially choose the support points and update the weights of support points of the design. The proposed algorithm is computationally efficient with guaranteed convergence property. Numerical examples are conducted to evaluate the feasibility and computational efficiency of the proposed algorithm. …

Regularized Determinantal Point Process (R-DPP)
Given a fixed $n\times d$ matrix $\mathbf{X}$, where $n\gg d$, we study the complexity of sampling from a distribution over all subsets of rows where the probability of a subset is proportional to the squared volume of the parallelopiped spanned by the rows (a.k.a. a determinantal point process). In this task, it is important to minimize the preprocessing cost of the procedure (performed once) as well as the sampling cost (performed repeatedly). To that end, we propose a new determinantal point process algorithm which has the following two properties, both of which are novel: (1) a preprocessing step which runs in time $O(\text{number-of-non-zeros}(\mathbf{X})\cdot\log n)+\text{poly}(d)$, and (2) a sampling step which runs in $\text{poly}(d)$ time, independent of the number of rows $n$. We achieve this by introducing a new regularized determinantal point process (R-DPP), which serves as an intermediate distribution in the sampling procedure by reducing the number of rows from $n$ to $\text{poly}(d)$. Crucially, this intermediate distribution does not distort the probabilities of the target sample. Our key novelty in defining the R-DPP is the use of a Poisson random variable for controlling the probabilities of different subset sizes, leading to new determinantal formulas such as the normalization constant for this distribution. Our algorithm has applications in many diverse areas where determinantal point processes have been used, such as machine learning, stochastic optimization, data summarization and low-rank matrix reconstruction. …

Feature-Label Memory Network
Deep learning typically requires training a very capable architecture using large datasets. However, many important learning problems demand an ability to draw valid inferences from small size datasets, and such problems pose a particular challenge for deep learning. In this regard, various researches on ‘meta-learning’ are being actively conducted. Recent work has suggested a Memory Augmented Neural Network (MANN) for meta-learning. MANN is an implementation of a Neural Turing Machine (NTM) with the ability to rapidly assimilate new data in its memory, and use this data to make accurate predictions. In models such as MANN, the input data samples and their appropriate labels from previous step are bound together in the same memory locations. This often leads to memory interference when performing a task as these models have to retrieve a feature of an input from a certain memory location and read only the label information bound to that location. In this paper, we tried to address this issue by presenting a more robust MANN. We revisited the idea of meta-learning and proposed a new memory augmented neural network by explicitly splitting the external memory into feature and label memories. The feature memory is used to store the features of input data samples and the label memory stores their labels. Hence, when predicting the label of a given input, our model uses its feature memory unit as a reference to extract the stored feature of the input, and based on that feature, it retrieves the label information of the input from the label memory unit. In order for the network to function in this framework, a new memory-writingmodule to encode label information into the label memory in accordance with the meta-learning task structure is designed. Here, we demonstrate that our model outperforms MANN by a large margin in supervised one-shot classification tasks using Omniglot and MNIST datasets. …

Decision Tree Based Missing Value Imputation Technique (DMI)
Decision tree based Missing value Imputation technique’ (DMI) makes use of an EM algorithm and a decision tree (DT) algorithm. …

NestDNN
Mobile vision systems such as smartphones, drones, and augmented-reality headsets are revolutionizing our lives. These systems usually run multiple applications concurrently and their available resources at runtime are dynamic due to events such as starting new applications, closing existing applications, and application priority changes. In this paper, we present NestDNN, a framework that takes the dynamics of runtime resources into account to enable resource-aware multi-tenant on-device deep learning for mobile vision systems. NestDNN enables each deep learning model to offer flexible resource-accuracy trade-offs. At runtime, it dynamically selects the optimal resource-accuracy trade-off for each deep learning model to fit the model’s resource demand to the system’s available runtime resources. In doing so, NestDNN efficiently utilizes the limited resources in mobile vision systems to jointly maximize the performance of all the concurrently running applications. Our experiments show that compared to the resource-agnostic status quo approach, NestDNN achieves as much as 4.2% increase in inference accuracy, 2.0x increase in video frame processing rate and 1.7x reduction on energy consumption. …

Attention Branch Network (ABN)
Visual explanation enables human to understand the decision making of Deep Convolutional Neural Network (CNN), but it is insufficient to contribute the performance improvement. In this paper, we focus on the attention map for visual explanation, which represents high response value as the important region in image recognition. This region significantly improves the performance of CNN by introducing an attention mechanism that focuses on a specific region in an image. In this work, we propose Attention Branch Network (ABN), which extends the top-down visual explanation model by introducing a branch structure with an attention mechanism. ABN can be applicable to several image recognition tasks by introducing a branch for attention mechanism and is trainable for the visual explanation and image recognition in end-to-end manner. We evaluate ABN on several image recognition tasks such as image classification, fine-grained recognition, and multiple facial attributes recognition. Experimental results show that ABN can outperform the accuracy of baseline models on these image recognition tasks while generating an attention map for visual explanation.
Embedding Human Knowledge in Deep Neural Network via Attention Map …

Payoff Dynamical Model (PDM)
We consider that at every instant each member of a population, which we refer to as an agent, selects one strategy out of a finite set. The agents are nondescript, and their strategy choices are described by the so-called population state vector, whose entries are the portions of the population selecting each strategy. Likewise, each entry constituting the so-called payoff vector is the reward attributed to a strategy. We consider that a general finite-dimensional nonlinear dynamical system, denoted as payoff dynamical model (PDM), describes a mechanism that determines the payoff as a causal map of the population state. A bounded-rationality protocol, inspired primarily on evolutionary biology principles, governs how each agent revises its strategy repeatedly based on complete or partial knowledge of the population state and payoff. The population is protocol-homogeneous but is otherwise strategy-heterogeneous considering that the agents are allowed to select distinct strategies concurrently. A stochastic mechanism determines the instants when agents revise their strategies, but we consider that the population is large enough that, with high probability, the population state can be approximated with arbitrary accuracy uniformly over any finite horizon by a so-called (deterministic) mean population state. We propose an approach that takes advantage of passivity principles to obtain sufficient conditions determining, for a given protocol and PDM, when the mean population state is guaranteed to converge to a meaningful set of equilibria, which could be either an appropriately defined extension of Nash’s for the PDM or a perturbed version of it. By generalizing and unifying previous work, our framework also provides a foundation for future work. …

GP-DRF
Deep Gaussian processes (DGP) have appealing Bayesian properties, can handle variable-sized data, and learn deep features. Their limitation is that they do not scale well with the size of the data. Existing approaches address this using a deep random feature (DRF) expansion model, which makes inference tractable by approximating DGPs. However, DRF is not suitable for variable-sized input data such as trees, graphs, and sequences. We introduce the GP-DRF, a novel Bayesian model with an input layer of GPs, followed by DRF layers. The key advantage is that the combination of GP and DRF leads to a tractable model that can both handle a variable-sized input as well as learn deep long-range dependency structures of the data. We provide a novel efficient method to simultaneously infer the posterior of GP’s latent vectors and infer the posterior of DRF’s internal weights and random frequencies. Our experiments show that GP-DRF outperforms the standard GP model and DRF model across many datasets. Furthermore, they demonstrate that GP-DRF enables improved uncertainty quantification compared to GP and DRF alone, with respect to a Bhattacharyya distance assessment. Source code is available at https://…/GP_DRF. …