With the growth of content on social media networks, enterprises and services providers have become interested in identifying the questions of their customers. Tracking these questions become very challenging with the growth of text that grows directly proportional to the increase of Arabic users thus making it very difficult to be tracked manually. By automatic identifying the questions seeking answers on the social media networks and defining their category, we can automatically answer them by finding an existing answer or even routing them to those responsible for answering those questions in the customer service. This will result in saving the time and the effort and enhancing the customer feedback and improving the business. In this paper, we have implemented a binary classifier to classify Arabic text to either question seeking answer or not. We have added emotional based features to the state of the art features. Experimental evaluation has done and showed that these emotional features have improved the accuracy of the classifier.
The Covid-19 pandemic has made clear the need to improve modern multivariate time-series forecasting models. Current state of the art predictions of future daily deaths and, especially, hospital resource usage have confidence intervals that are unacceptably wide. Policy makers and hospitals require accurate forecasts to make informed decisions on passing legislation and allocating resources. We used US county-level data on daily deaths and population statistics to forecast future deaths. We extended the SIR epidemiological model to a novel model we call the PECAIQR model. It adds several new variables and parameters to the naive SIR model by taking into account the ramifications of the partial quarantining implemented in the US. We fitted data to the model parameters with numerical integration. Because of the fit degeneracy in parameter space and non-constant nature of the parameters, we developed several methods to optimize our fit, such as training on the data tail and training on specific policy regimes. We use cross-validation to tune our hyper parameters at the county level and generate a CDF for future daily deaths. For predictions made from training data up to May 25th, we consistently obtained an averaged pinball loss score of 0.096 on a 14 day forecast. We finally present examples of possible avenues for utility from our model. We generate longer-time horizon predictions over various 1-month windows in the past, forecast how many medical resources such as ventilators and ICU beds will be needed in counties, and evaluate the efficacy of our model in other countries.
We propose a novel mixture-of-experts class to optimize computer vision models in accordance with data transfer limitations at test time. Our approach postulates that the minimum acceptable amount of data allowing for highly-accurate results can vary for different input space partitions. Therefore, we consider mixtures where experts require different amounts of data, and train a sparse gating function to divide the input space for each expert. By appropriate hyperparameter selection, our approach is able to bias mixtures of experts towards selecting specific experts over others. In this way, we show that the data transfer optimization between visual sensing and processing can be solved as a convex optimization problem.To demonstrate the relation between data availability and performance, we evaluate biased mixtures on a range of mainstream computer vision problems, namely: (i) single shot detection, (ii) image super resolution, and (iii) realtime video action classification. For all cases, and when experts constitute modified baselines to meet different limits on allowed data utility, biased mixtures significantly outperform previous work optimized to meet the same constraints on available data.
Videos of actions are complex spatio-temporal signals, containing rich compositional structures. Current generative models are limited in their ability to generate examples of object configurations outside the range they were trained on. Towards this end, we introduce a generative model (AG2Vid) based on Action Graphs, a natural and convenient structure that represents the dynamics of actions between objects over time. Our AG2Vid model disentangles appearance and position features, allowing for more accurate generation. AG2Vid is evaluated on the CATER and Something-Something datasets and outperforms other baselines. Finally, we show how Action Graphs can be used for generating novel compositions of unseen actions.
We propose an algorithm which predicts each subsequent time step relative to the previous time step of intractable short rate model (when adjusted for drift and overall distribution of previous percentile result) and show that the method achieves superior outcomes to the unbiased estimate both on the trained dataset and different validation data.
The goal of generative models is to learn the intricate relations between the data to create new simulated data, but current approaches fail in very high dimensions. When the true data generating process is based on physical processes these impose symmetries and constraints, and the generative model can be created by learning an effective description of the underlying physics, which enables scaling of the generative model to very high dimensions. In this work we propose Lagrangian Deep Learning (LDL) for this purpose, applying it to learn outputs of cosmological hydrodynamical simulations. The model uses layers of Lagrangian displacements of particles describing the observables to learn the effective physical laws. The displacements are modeled as the gradient of an effective potential, which explicitly satisfies the translational and rotational invariance. The total number of learned parameters is only of order 10, and they can be viewed as effective theory parameters. We combine N-body solver FastPM with LDL and apply them to a wide range of cosmological outputs, from the dark matter to the stellar maps, gas density and temperature. The computational cost of LDL is nearly four orders of magnitude lower than the full hydrodynamical simulations, yet it outperforms it at the same resolution. We achieve this with only of order 10 layers from the initial conditions to the final output, in contrast to typical cosmological simulations with thousands of time steps. This opens up the possibility of analyzing cosmological observations entirely within this framework, without the need for large dark-matter simulations.
With the increasing demand for more and more data, the federated learning (FL) methods, which try to utilize highly distributed on-device local data in the training process, have been proposed.However, fledgling services provided by startup companies not only have limited number of clients, but also have minimal resources for constant communications between the server and multiple clients. In addition, in a real-world environment where the user pool changes dynamically, the FL system must be able to efficiently utilize rapid inflow and outflow of users, while at the same time experience minimal bottleneck due to network delays of multiple users. In this respect, we amend the federated learning scenario to a more flexible asynchronous edge learning. To solve the aforementioned learning problems, we propose an asynchronous model-based communication method with knowledge distillation. In particular, we dub our knowledge distillation scheme as "cloned distillation" and explain how it is different from other knowledge distillation method. In brief, we found that in knowledge distillation between the teacher and the student there exist two contesting traits in the student: to attend to the teacher's knowledge or to retain its own knowledge exclusive to the teacher. And in this edge learning scenario, the attending property should be amplified rather than the retaining property, because teachers are dispatched to the users to learn from them and recollected at the server to teach the core model. Our asynchronous edge learning method can elastically handle the dynamic inflow and outflow of users in a service with minimal communication cost, operate with essentially no bottleneck due to user delay, and protect user's privacy. Also we found that it is robust to users who behave abnormally or maliciously.
This paper addresses the problem of efficiently achieving visual predictive control tasks. To this end, a memory of motion, containing a set of trajectories built off-line, is used for leveraging precomputation and dealing with difficult visual tasks. Standard regression techniques, such as k-nearest neighbors and Gaussian process regression, are used to query the memory and provide on-line a warm-start and a way point to the control optimization process. The proposed technique allows the control scheme to achieve high performance and, at the same time, keep the computational time limited. Simulation and experimental results, carried out with a 7-axis manipulator, show the effectiveness of the approach.
There has been remarkable progress in the application of deep learning to 3D point cloud registration in recent years. Despite their success, these approaches tend to have poor generalization properties when attempting to align unseen point clouds at test time. PointNetLK has proven the exception to this rule by leveraging the intrinsic generalization properties of the Lucas & Kanade (LK) image alignment algorithm to point cloud registration. The approach relies heavily upon the estimation of a gradient through finite differentiation -- a strategy that is inherently ill-conditioned and highly sensitive to the step-size choice. To avoid these problems, we propose a deterministic PointNetLK method that uses analytical gradients. We also develop several strategies to improve large-volume point cloud processing. We compare our approach to canonical PointNetLK and other state-of-the-art methods and demonstrate how our approach provides accurate, reliable registration with high fidelity. Extended experiments on noisy, sparse, and partial point clouds depict the utility of our approach for many real-world scenarios. Further, the decomposition of the Jacobian matrix affords the reuse of feature embeddings for alternate warp functions.
Species living in the extreme cold environment fight against the harsh conditions by virtue of antifreeze proteins (AFPs), that manipulates the freezing mechanism of water in more than one way. This amazing nature of AFP turns out to be extremely useful in a number of industrial and medical applications. The lack of similarity in their structure and sequence makes their prediction an arduous task and identifying them experimentally in the wet-lab is time consuming and expensive. In this research, we propose a computational framework for the prediction of AFPs which is essentially based on a sample-specific classification method using the sparse reconstruction. A linear model and an over-complete dictionary matrix of known AFPs is used to predict sparse class-label vector which provides sample-association score. Delta-rule is applied for the reconstruction of two pseudo-samples using lower and upper parts of sample-association vector and based on the minimum recovery score, class labels are assigned. We compare our approach with contemporary methods on a standard dataset and the proposed method is found to outperform in terms of Matthews correlation coefficient and Youden's index. The MATLAB implementation of proposed method is available at author's github page https://github.com/Shujaat123/AFP-SRC.