Egocentric action anticipation consists in understanding which objects the camera wearer will interact with in the near future and which actions they will perform. We tackle the problem proposing an architecture able to anticipate actions at multiple temporal scales using two LSTMs to 1) summarize the past, and 2) formulate predictions about the future. The input video is processed considering three complimentary modalities: appearance (RGB), motion (optical flow) and objects (object-based features). Modality-specific predictions are fused using a novel Modality ATTention (MATT) mechanism which learns to weigh modalities in an adaptive fashion. Extensive evaluations on two large-scale benchmark datasets show that our method outperforms prior art by up to +7% on the challenging EPIC-KITCHENS dataset including more than 2500 actions, and generalizes to EGTEA Gaze+. Our approach is also shown to generalize to the tasks of early action recognition and action recognition. At the moment of submission, our method is ranked first in the leaderboard of the EPIC-KITCHENS egocentric action anticipation challenge.

Reading Comprehension has received significant attention in recent years as high quality Question Answering (QA) datasets have become available. Despite state-of-the-art methods achieving strong overall accuracy, Multi-Hop (MH) reasoning remains particularly challenging. To address MH-QA specifically, we propose a Deep Reinforcement Learning based method capable of learning sequential reasoning across large collections of documents so as to pass a query-aware, fixed-size context subset to existing models for answer extraction. Our method is comprised of two stages: a linker, which decomposes the provided support documents into a graph of sentences, and an extractor, which learns where to look based on the current question and already-visited sentences. The result of the linker is a novel graph structure at the sentence level that preserves logical flow while still allowing rapid movement between documents. Importantly, we demonstrate that the sparsity of the resultant graph is invariant to context size. This translates to fewer decisions required from the Deep-RL trained extractor, allowing the system to scale effectively to large collections of documents. The importance of sequential decision making in the document traversal step is demonstrated by comparison to standard IE methods, and we additionally introduce a BM25-based IR baseline that retrieves documents relevant to the query only. We examine the integration of our method with existing models on the recently proposed QAngaroo benchmark and achieve consistent increases in accuracy across the board, as well as a 2-3x reduction in training time.

In recent studies, several asymptotic upper bounds on generalization errors on deep neural networks (DNNs) are theoretically derived. These bounds are functions of several norms of weights of the DNNs, such as the Frobenius and spectral norms, and they are computed for weights grouped according to either input and output channels of the DNNs. In this work, we conjecture that if we can impose multiple constraints on weights of DNNs to upper bound the norms of the weights, and train the DNNs with these weights, then we can attain empirical generalization errors closer to the derived theoretical bounds, and improve accuracy of the DNNs. To this end, we pose two problems. First, we aim to obtain weights whose different norms are all upper bounded by a constant number, e.g. 1.0. To achieve these bounds, we propose a two-stage renormalization procedure; (i) normalization of weights according to different norms used in the bounds, and (ii) reparameterization of the normalized weights to set a constant and finite upper bound of their norms. In the second problem, we consider training DNNs with these renormalized weights. To this end, we first propose a strategy to construct joint spaces (manifolds) of weights according to different constraints in DNNs. Next, we propose a fine-grained SGD algorithm (FG-SGD) for optimization on the weight manifolds to train DNNs with assurance of convergence to minima. Experimental results show that image classification accuracy of baseline DNNs can be boosted using FG-SGD on collections of manifolds identified by multiple constraints.

Advertising and feed ranking are essential to many Internet companies such as Facebook and Sina Weibo. Among many real-world advertising and feed ranking systems, click through rate (CTR) prediction plays a central role. There are many proposed models in this field such as logistic regression, tree based models, factorization machine based models and deep learning based CTR models. However, many current works calculate the feature interactions in a simple way such as Hadamard product and inner product and they care less about the importance of features. In this paper, a new model named FiBiNET as an abbreviation for Feature Importance and Bilinear feature Interaction NETwork is proposed to dynamically learn the feature importance and fine-grained feature interactions. On the one hand, the FiBiNET can dynamically learn the importance of features via the Squeeze-Excitation network (SENET) mechanism; on the other hand, it is able to effectively learn the feature interactions via bilinear function. We conduct extensive experiments on two real-world datasets and show that our shallow model outperforms other shallow models such as factorization machine(FM) and field-aware factorization machine(FFM). In order to improve performance further, we combine a classical deep neural network(DNN) component with the shallow model to be a deep model. The deep FiBiNET consistently outperforms the other state-of-the-art deep models such as DeepFM and extreme deep factorization machine(XdeepFM).

We investigate the use of ellipsoidal trust region constraints for second-order optimization of neural networks. This approach can be seen as a higher-order counterpart of adaptive gradient methods, which we here show to be interpretable as first-order trust region methods with ellipsoidal constraints. In particular, we show that the preconditioning matrix used in RMSProp and Adam satisfies the necessary conditions for convergence of (first- and) second-order trust region methods and report that this ellipsoidal constraint constantly outperforms its spherical counterpart in practice. We furthermore set out to clarify the long-standing question of the potential superiority of Newton methods in deep learning. In this regard, we run extensive benchmarks across different datasets and architectures to find that comparable performance to gradient descent algorithms can be achieved but using Hessian information does not give rise to better limit points and comes at the cost of increased hyperparameter tuning.

Underline the presenter's name - Affiliation: Provide authors' institutions and addresses. In the case of multiple institutions, identify them by roman numbers - The main body of the abstract should be structured with the following sub-headings: Background, Aim, Methodology, Findings, and Conclusion. It's important to also include the corresponding author's contacts: e-mail and telephone number.

This essay reviews human observer-based methods employed in shark spotting in Muizenberg Beach. It investigates Machine Learning methods for automated shark detection with the aim of enhancing human observation. A questionnaire and interview were used to collect information about shark spotting, the motivation of the actual Shark Spotter program and its limitations. We have defined a list of desirable properties for our model and chosen the adequate mathematical techniques. The preliminary results of the research show that we can expect to extract useful information from shark images despite the geometric transformations that sharks perform, its features do not change. To conclude, we have partially implemented our model; the remaining implementation requires dataset.

In recent years, the rapid growth in technology has increased the opportunity for longitudinal human behavioral studies. Rich multimodal data, from wearables like Fitbit, online social networks, mobile phones etc. can be collected in natural environments. Uncovering the underlying low-dimensional structure of noisy multi-way data in an unsupervised setting is a challenging problem. Tensor factorization has been successful in extracting the interconnected low-dimensional descriptions of multi-way data. In this paper, we apply non-negative tensor factorization on a real-word wearable sensor data, StudentLife, to find latent temporal factors and group of similar individuals. Meta data is available for the semester schedule, as well as the individuals' performance and personality. We demonstrate that non-negative tensor factorization can successfully discover clusters of individuals who exhibit higher academic performance, as well as those who frequently engage in leisure activities. The recovered latent temporal patterns associated with these groups are validated against ground truth data to demonstrate the accuracy of our framework.

Deep neural networks (DNNs) have been quite successful in solving many complex learning problems. However, DNNs tend to have a large number of learning parameters, leading to a large memory and computation requirement. In this paper, we propose a model compression framework for efficient training and inference of deep neural networks on embedded systems. Our framework provides data structures and kernels for OpenCL-based parallel forward and backward computation in a compressed form. In particular, our method learns sparse representations of parameters using $\ell_1$-based sparse coding while training, storing them in compressed sparse matrices. Unlike the previous works, our method does not require a pre-trained model as an input and therefore can be more versatile for different application environments. Even though the use of $\ell_1$-based sparse coding for model compression is not new, we show that it can be far more effective than previously reported when we use proximal point algorithms and the technique of debiasing. Our experiments show that our method can produce minimal learning models suitable for small embedded devices.

Data-driven methods such as convolutional neural networks (CNNs) are known to deliver state-of-the-art performance on image recognition tasks when the training data are abundant. However, in some instances, such as change detection in remote sensing images, annotated data cannot be obtained in sufficient quantities. In this work, we propose a simple and efficient method for creating realistic targeted synthetic datasets in the remote sensing domain, leveraging the opportunities offered by game development engines. We provide a description of the pipeline for procedural geometry generation and rendering as well as an evaluation of the efficiency of produced datasets in a change detection scenario. Our evaluations demonstrate that our pipeline helps to improve the performance and convergence of deep learning models when the amount of real-world data is severely limited.