The widespread adoption of deep learning is often attributed to its automatic feature construction with minimal inductive bias. However, in many real-world tasks, the learned function is intended to satisfy domain-specific constraints. We focus on monotonicity constraints, which are common and require that the function's output increases with increasing values of specific input features. We develop a counterexample-guided technique to provably enforce monotonicity constraints at prediction time. Additionally, we propose a technique to use monotonicity as an inductive bias for deep learning. It works by iteratively incorporating monotonicity counterexamples in the learning process. Contrary to prior work in monotonic learning, we target general ReLU neural networks and do not further restrict the hypothesis space. We have implemented these techniques in a tool called COMET. Experiments on real-world datasets demonstrate that our approach achieves state-of-the-art results compared to existing monotonic learners, and can improve the model quality compared to those that were trained without taking monotonicity constraints into account.
Exponential-family harmoniums (EFHs), which extend restricted Boltzmann machines (RBMs) from Bernoulli random variables to other exponential families (Welling et al., 2005), are generative models that can be trained with unsupervised-learning techniques, like contrastive divergence (Hinton et al. 2006; Hinton, 2002), as density estimators for static data. Methods for extending RBMs--and likewise EFHs--to data with temporal dependencies have been proposed previously (Sutskever and Hinton, 2007; Sutskever et al., 2009), the learning procedure being validated by qualitative assessment of the generative model. Here we propose and justify, from a very different perspective, an alternative training procedure, proving sufficient conditions for optimal inference under that procedure. The resulting algorithm can be learned with only forward passes through the data--backprop-through-time is not required, as in previous approaches. The proof exploits a recent result about information retention in density estimators (Makin and Sabes, 2015), and applies it to a "recurrent EFH" (rEFH) by induction. Finally, we demonstrate optimality by simulation, testing the rEFH: (1) as a filter on training data generated with a linear dynamical system, the position of which is noisily reported by a population of "neurons" with Poisson-distributed spike counts; and (2) with the qualitative experiments proposed by Sutskever et al. (2009).
Existing methods for instance segmentation in videos typically involve multi-stage pipelines that follow the tracking-by-detection paradigm and model a video clip as a sequence of images. Multiple networks are used to detect objects in individual frames, and then associate these detections over time. Hence, these methods are often non-end-to-end trainable and highly tailored to specific tasks. In this paper, we propose a different approach that is well-suited to a variety of tasks involving instance segmentation in videos. In particular, we model a video clip as a single 3D spatio-temporal volume, and propose a novel approach that segments and tracks instances across space and time in a single stage. Our problem formulation is centered around the idea of spatio-temporal embeddings which are trained to cluster pixels belonging to a specific object instance over an entire video clip. To this end, we introduce (i) novel mixing functions that enhance the feature representation of spatio-temporal embeddings, and (ii) a single-stage, proposal-free network that can reason about temporal context. Our network is trained end-to-end to learn spatio-temporal embeddings as well as parameters required to cluster these embeddings, thus simplifying inference. Our method achieves state-of-the-art results across multiple datasets and tasks.
The supervised learning paradigm is limited by the cost - and sometimes the impracticality - of data collection and labeling in multiple domains. Self-supervised learning, a paradigm which exploits the structure of unlabeled data to create learning problems that can be solved with standard supervised approaches, has shown great promise as a pretraining or feature learning approach in fields like computer vision and time series processing. In this work, we present self-supervision strategies that can be used to learn informative representations from multivariate time series. One successful approach relies on predicting whether time windows are sampled from the same temporal context or not. As demonstrated on a clinically relevant task (sleep scoring) and with two electroencephalography datasets, our approach outperforms a purely supervised approach in low data regimes, while capturing important physiological information without any access to labels.
A novel algorithm is proposed to solve the sample-based optimal transport problem. An adversarial formulation of the push-forward condition uses a test function built as a convolution between an adaptive kernel and an evolving probability distribution $\nu$ over a latent variable $b$. Approximating this convolution by its simulation over evolving samples $b^i(t)$ of $\nu$, the parameterization of the test function reduces to determining the flow of these samples. This flow, discretized over discrete time steps $t_n$, is built from the composition of elementary maps. The optimal transport also follows a flow that, by duality, must follow the gradient of the test function. The representation of the test function as the Monte Carlo simulation of a distribution makes the algorithm robust to dimensionality, and its evolution under a memory-less flow produces rich, complex maps from simple parametric transformations. The algorithm is illustrated with numerical examples.
We design a physics-aware auto-encoder to specifically reduce the dimensionality of solutions arising from convection-dominated nonlinear physical systems. Although existing nonlinear manifold learning methods seem to be compelling tools to reduce the dimensionality of data characterized by a large Kolmogorov n-width, they typically lack a straightforward mapping from the latent space to the high-dimensional physical space. Moreover, the realized latent variables are often hard to interpret. Therefore, many of these methods are often dismissed in the reduced order modeling of dynamical systems governed by the partial differential equations (PDEs). Accordingly, we propose an auto-encoder type nonlinear dimensionality reduction algorithm. The unsupervised learning problem trains a diffeomorphic spatio-temporal grid, that registers the output sequence of the PDEs on a non-uniform parameter/time-varying grid, such that the Kolmogorov n-width of the mapped data on the learned grid is minimized. We demonstrate the efficacy and interpretability of our approach to separate convection/advection from diffusion/scaling on various manufactured and physical systems.
Properly modelling dynamic information that changes over time still is an open issue. Most modern knowledge bases are unable to represent relationships that are valid only during a given time interval. In this work, we revisit a previous extension to the hyperknowledge framework to deal with temporal facts and propose a temporal query language and engine. We validate our proposal by discussing a qualitative analysis of the modelling of a real-world use case in the Oil & Gas industry.
In our current web and mobile application development runtime nude image content detection is very important. This paper presents a runtime nudity detection method for web and mobile application development. We use two parameters to detect the nude content of an image. One is the number of skin pixels another is face region. A skin color model based on RGB, HSV color spaces are used to detect skin pixels in an image. Google vision api is used to detect the face region. By the percentage of skin regions and face regions an image is identified nude or not. The success of this algorithm exists in detecting skin regions and face regions. The skin detection algorithm can detect skin 95% accurately with a low false-positive rate and the google vision api for web and mobile applications can detect face 99% accurately with less than 1 second time. From the experimental analysis, we have seen that the proposed algorithm can detect 95% percent accurately the nudity of an image.
Motivation: DNA N6-methylation (6mA) in Adenine nucleotide is a post replication modification and is responsible for many biological functions. Experimental methods for genome wide 6mA site detection is an expensive and manual labour intensive process. Automated and accurate computational methods can help to identify 6mA sites in long genomes saving significant time and money. Results: Our study develops a convolutional neural network based tool i6mA-CNN capable of identifying 6mA sites in the rice genome. Our model coordinates among multiple types of features such as PseAAC inspired customized feature vector, multiple one hot representations and dinucleotide physicochemical properties. It achieves area under the receiver operating characteristic curve of 0.98 with an overall accuracy of 0.94 using 5 fold cross validation on benchmark dataset. Finally, we evaluate our model on two other plant genome 6mA site identification datasets besides rice. Results suggest that our proposed tool is able to generalize its ability of 6mA site identification on plant genomes irrespective of plant species. Availability: Web tool for this research can be found at: https://cutt.ly/Co6KuWG. Contact: rafeed@cse.uiu.ac.bd Supplementary information: Supplementary data (benchmark dataset, independent test dataset, comparison purpose dataset, trained model, physicochemical property values, attention mechanism details for motif finding) are available at https://cutt.ly/PpDdeDH.
With the increasing global popularity of self-driving cars, there is an immediate need for challenging real-world datasets for benchmarking and training various computer vision tasks such as 3D object detection. Existing datasets either represent simple scenarios or provide only day-time data. In this paper, we introduce a new challenging A*3D dataset which consists of RGB images and LiDAR data with significant diversity of scene, time, and weather. The dataset consists of high-density images ($\approx~10$ times more than the pioneering KITTI dataset), heavy occlusions, a large number of night-time frames ($\approx~3$ times the nuScenes dataset), addressing the gaps in the existing datasets to push the boundaries of tasks in autonomous driving research to more challenging highly diverse environments. The dataset contains $39\text{K}$ frames, $7$ classes, and $230\text{K}$ 3D object annotations. An extensive 3D object detection benchmark evaluation on the A*3D dataset for various attributes such as high density, day-time/night-time, gives interesting insights into the advantages and limitations of training and testing 3D object detection in real-world setting.