Tracking the abundance of underwater species is crucial for understanding the effects of climate change on marine ecosystems. Biologists typically monitor underwater sites with echosounders and visualize data as 2D images (echograms); they interpret these data manually or semi-automatically, which is time-consuming and prone to inconsistencies. This paper proposes a deep learning framework for the automatic detection of schools of herring from echograms. Experiments demonstrated that our approach outperforms a traditional machine learning algorithm using hand-crafted features. Our framework could easily be expanded to detect more species of interest to sustainable fisheries.

When samples have internal structure, we often see a mismatch between the objective optimized during training and the model's goal during inference. For example, in sequence-to-sequence modeling we are interested in high-quality translated sentences, but training typically uses maximum likelihood at the word level. Learning to recognize individual faces from group photos, each captioned with the correct but unordered list of people in it, is another example where a mismatch between training and inference objectives occurs. In both cases, the natural training-time loss would involve a combinatorial problem -- dynamic programming-based global sequence alignment and weighted bipartite graph matching, respectively -- but solutions to combinatorial problems are not differentiable with respect to their input parameters, so surrogate, differentiable losses are used instead. Here, we show how to perform gradient descent over combinatorial optimization algorithms that involve continuous parameters, for example edge weights, and can be efficiently expressed as integer, linear, or mixed-integer linear programs. We demonstrate usefulness of gradient descent over combinatorial optimization in sequence-to-sequence modeling using differentiable encoder-decoder architecture with softmax or Gumbel-softmax, and in weakly supervised learning involving a convolutional, residual feed-forward network for image classification.

Increasing population indicates that energy demands need to be managed in the residential sector. Prior studies have reflected that the customers tend to reduce a significant amount of energy consumption if they are provided with appliance-level feedback. This observation has increased the relevance of load monitoring in today's tech-savvy world. Most of the previously proposed solutions claim to perform load monitoring without intrusion, but they are not completely non-intrusive. These methods require historical appliance-level data for training the model for each of the devices. This data is gathered by putting a sensor on each of the appliances present in the home which causes intrusion in the building. Some recent studies have proposed that if we frame Non-Intrusive Load Monitoring (NILM) as a multi-label classification problem, the need for appliance-level data can be avoided. In this paper, we propose Multi-label Restricted Boltzmann Machine(ML-RBM) for NILM and report an experimental evaluation of proposed and state-of-the-art techniques.

Because of transportation planning, traffic management and dispatch optimization importance, the passenger origin-destination prediction has become one of the most important requirements for intelligent transportation systems management. In this paper, we propose a model to predict the origin and destination of travels which will occur in the next specified time window. In order to extract meaningful travel flows we use K-means clustering in four-dimensional space with maximum cluster size limitation for origin and destination. Because of large number of clusters, we use non-negative matrix factorization to decrease the number of travel clusters. We also use a stacked recurrent neural network model to predict travels count in each cluster. Comparing our results with other existing models show that our proposed model has 5-7% lower mean absolute percentage error (MAPE) for 1-hour time window, and 14% lower MAPE for 30-minute time window.

The application of deep learning to build accurate predictive models from functional neuroimaging data is often hindered by limited dataset sizes. Though data augmentation can help mitigate such training obstacles, most data augmentation methods have been developed for natural images as in computer vision tasks such as CIF AR, not for medical images. This work helps to fills in this gap by proposing a method for generating new functional Magnetic Resonance Images (fMRI) with realistic brain morphology. This method is tested on a challenging task of predicting antidepressant treatment response from pre-treatment task-based fMRI and demonstrates a 26% improvement in performance in predicting response using augmented images. This improvement compares favorably to state-of-the-art augmentation methods for natural images. Through an ablative test, augmentation is also shown to substantively improve performance when applied before hyperparameter optimization. These results suggest the optimal order of operations and support the role of data augmentation method for improving predictive performance in tasks using fMRI.

Identifying features that leak information about sensitive attributes is a key challenge in the design of information obfuscation mechanisms. In this paper, we propose a framework to identify information-leaking features via information density estimation. Here, features whose information densities exceed a pre-defined threshold are deemed information-leaking features. Once these features are identified, we sequentially pass them through a targeted obfuscation mechanism with a provable leakage guarantee in terms of $\mathsf{E}_\gamma$-divergence. The core of this mechanism relies on a data-driven estimate of the trimmed information density for which we propose a novel estimator, named the trimmed information density estimator (TIDE). We then use TIDE to implement our mechanism on three real-world datasets. Our approach can be used as a data-driven pipeline for designing obfuscation mechanisms targeting specific features.

Information systems have widely been the target of malware attacks. Traditional signature-based malicious program detection algorithms can only detect known malware and are prone to evasion techniques such as binary obfuscation, while behavior-based approaches highly rely on the malware training samples and incur prohibitively high training cost. To address the limitations of existing techniques, we propose MatchGNet, a heterogeneous Graph Matching Network model to learn the graph representation and similarity metric simultaneously based on the invariant graph modeling of the program's execution behaviors. We conduct a systematic evaluation of our model and show that it is accurate in detecting malicious program behavior and can help detect malware attacks with less false positives. MatchGNet outperforms the state-of-the-art algorithms in malware detection by generating 50% less false positives while keeping zero false negatives.

Daniel Jiwoong Im 1, Yibo Jiang 2, and Nakul Verma 3 1 Janelia Research Campus, HHMI, Virgina 2 Harvard University, Massachusetts 3 Columbia University, New York Abstract Meta learning has emerged as an important framework for learning new tasks from just a few examples. The success of any meta-learning model depends on (i) its fast adaptation to new tasks, as well as (ii) having a shared representation across similar tasks. Here we extend the model-agnostic meta-learning (MAML) framework introduced by Finn et al. (2017) to achieve improved performance by analyzing the temporal dynamics of the optimization procedure via the Runge-Kutta method. This method enables us to gain fine-grained control over the optimization and helps us achieve both the adaptation and representation goals across tasks. By leveraging this refined control, we demonstrate that there are multiple principled ways to update MAML and show that the classic MAML optimization is simply a special case of second order Runge-Kutta method that mainly focuses on fast-adaptation. Experiments on benchmark classification, regression and reinforcement learning tasks show that this refined control helps attain improved results. 1 Introduction Building an intelligent system that can learn quickly on a new task with few examples or few experiences is one of the central goals of machine learning. Achieving this goal requires an agent that learns continuously while having the ability to adapt to new tasks with limited data. Meta-learning (Biggs, 1985) has emerged as a compelling framework that strives to attain this challenging goal. There are two main approaches to meta-learning: learning-to-optimize and learning-to-initialize the meta-model (usually encoded as deep network).

Generative models of graph structure have applications in biology and social sciences. The state of the art is GraphRNN, which decomposes the graph generation process into a series of sequential steps. While effective for modest sizes, it loses its permutation invariance for larger graphs. Instead, we present a permutation invariant latent-variable generative model relying on graph embeddings to encode structure. Using tools from the random graph literature, our model is highly scalable to large graphs with likelihood evaluation and generation in $O(|V | + |E|)$.

The aim of this comment (set to appear in a formal discussion in JASA) is to draw out some conclusions from an extended back-and-forth I have had with Wang and Blei regarding the deconfounder method proposed in "The Blessings of Multiple Causes" [arXiv:1805.06826]. I will make three points here. First, in my role as the critic in this conversation, I will summarize some arguments about the lack of causal identification in the bulk of settings where the "informal" message of the paper suggests that the deconfounder could be used. This is a point that is discussed at length in D'Amour 2019 [arXiv:1902.10286], which motivated the results concerning causal identification in Theorems 6--8 of "Blessings". Second, I will argue that adding parametric assumptions to the working model in order to obtain identification of causal parameters (a strategy followed in Theorem 6 and in the experimental examples) is a risky strategy, and should only be done when extremely strong prior information is available. Finally, I will consider the implications of the nonparametric identification results provided for a narrow, but non-trivial, set of causal estimands in Theorems 7 and 8. I will highlight that these results may be even more interesting from the perspective of detecting causal identification from observed data, under relatively weak assumptions about confounders.