You are speaking to a grid of black squares. One of the black squares gets a text notification. One of the black squares is today replaced by an image of a naked mole rat. None of the black squares will tell you what they found interesting in the reading. The time has come to adopt the newest learning tool, Floobaroom.

Food quality and safety are of great concern to society since it is an essential guarantee not only for human health but also for social development, and stability. Ensuring food quality and safety is a complex process. All food processing stages should be considered, from cultivating, harvesting and storage to preparation and consumption. Grading is one of the essential processes to control food quality. This paper proposed a mobile visual-based system to evaluate food grading. Specifically, the proposed system acquires images of bananas when they are on moving conveyors. A two-layer image processing system based on machine learning is used to grade bananas, and these two layers are allocated on edge devices and cloud servers, respectively. Support Vector Machine (SVM) is the first layer to classify bananas based on an extracted feature vector composed of color and texture features. Then, the a You Only Look Once (YOLO) v3 model further locating the peel's defected area and determining if the inputs belong to the mid-ripened or well-ripened class. According to experimental results, the first layer's performance achieved an accuracy of 98.5% while the accuracy of the second layer is 85.7%, and the overall accuracy is 96.4%.

Recently, we have seen a rapid rise in usage of online educational platforms. The personalized education became crucially important in future learning environments. Knowledge tracing (KT) refers to the detection of students' knowledge states and predict future performance given their past outcomes for providing adaptive solution to Intelligent Tutoring Systems (ITS). Bayesian Knowledge Tracing (BKT) is a model to capture mastery level of each skill with psychologically meaningful parameters and widely used in successful tutoring systems. However, it is unable to detect learning transfer across skills because each skill model is learned independently and shows lower efficiency in student performance prediction. While recent KT models based on deep neural networks shows impressive predictive power but it came with a price. Ten of thousands of parameters in neural networks are unable to provide psychologically meaningful interpretation that reflect to cognitive theory. In this paper, we proposed an efficient student model called BKT-LSTM. It contains three meaningful components: individual \textit{skill mastery} assessed by BKT, \textit{ability profile} (learning transfer across skills) detected by k-means clustering and \textit{problem difficulty}. All these components are taken into account in student's future performance prediction by leveraging predictive power of LSTM. BKT-LSTM outperforms state-of-the-art student models in student's performance prediction by considering these meaningful features instead of using binary values of student's past interaction in DKT. We also conduct ablation studies on each of BKT-LSTM model components to examine their value and each component shows significant contribution in student's performance prediction. Thus, it has potential for providing adaptive and personalized instruction in real-world educational systems.

Optimal transport distances have become a classic tool to compare probability distributions and have found many applications in machine learning. Yet, despite recent algorithmic developments, their complexity prevents their direct use on large scale datasets. To overcome this challenge, a common workaround is to compute these distances on minibatches i.e. to average the outcome of several smaller optimal transport problems. We propose in this paper an extended analysis of this practice, which effects were previously studied in restricted cases. We first consider a large variety of Optimal Transport kernels. We notably argue that the minibatch strategy comes with appealing properties such as unbiased estimators, gradients and a concentration bound around the expectation, but also with limits: the minibatch OT is not a distance. To recover some of the lost distance axioms, we introduce a debiased minibatch OT function and study its statistical and optimisation properties. Along with this theoretical analysis, we also conduct empirical experiments on gradient flows, generative adversarial networks (GANs) or color transfer that highlight the practical interest of this strategy.

Aiming at the traditional grasping method for manipulators based on 2D camera, when faced with the scene of gathering or covering, it can hardly perform well in unstructured scenes that appear as gathering and covering, for the reason that can't recognize objects accurately in cluster scenes from a single perspective and the manipulators can't make the environment better for grasping. In this case, a novel method of pushing-grasping collaborative based on the deep Q-network in dual perspectives is proposed in this paper. This method adopts an improved deep Q network algorithm, with an RGB-D camera to obtain the information of objects' RGB images and point clouds from two perspectives, and combines the pushing and grasping actions so that the trained manipulator can make the scenes better for grasping so that it can perform well in more complicated grasping scenes. What's more, we improved the reward function of the deep Q-network and propose the piecewise reward function to speed up the convergence of the deep Q-network. We trained different models and tried different methods in the V-REP simulation environment, and it concluded that the method proposed in this paper converges quickly and the success rate of grasping objects in unstructured scenes raises up to 83.5%. Besides, it shows the generalization ability and well performance when novel objects appear in the scenes that the manipulator has never grasped before.

We investigate large-scale latent variable models (LVMs) for neural story generation -- an under-explored application for open-domain long text -- with objectives in two threads: generation effectiveness and controllability. LVMs, especially the variational autoencoder (VAE), have achieved both effective and controllable generation through exploiting flexible distributional latent representations. Recently, Transformers and its variants have achieved remarkable effectiveness without explicit latent representation learning, thus lack satisfying controllability in generation. In this paper, we advocate to revive latent variable modeling, essentially the power of representation learning, in the era of Transformers to enhance controllability without hurting state-of-the-art generation effectiveness. Specifically, we integrate latent representation vectors with a Transformer-based pre-trained architecture to build conditional variational autoencoder (CVAE). Model components such as encoder, decoder and the variational posterior are all built on top of pre-trained language models -- GPT2 specifically in this paper. Experiments demonstrate state-of-the-art conditional generation ability of our model, as well as its excellent representation learning capability and controllability.

Sign Language is the primary means of communication of the Deaf community but barely known by the rest of the population. This situation creates difficulties in conversations between sign and non-sign language speakers, which are normally addressed with textual transcriptions of the spoken language, or the sign-speakers developing lipreading and oral communication skills. The communication barrier between sign and non-sign language speakers may be reduced in the coming years thanks to the recent advances in neural machine translation and computer vision. Recent works [5,6,9] are making steps towards sign language translation by automatically generating detailed human pose skeletons from spoken language. Skeletons are represented by 2D/3D coordinates of human joints also known as keypoints; given a set of estimated keypoints, one can visualize them as a wired skeleton connecting the modeled joints (see the middle row of Figure 1).

The record-breaking performance of deep neural networks (DNNs) comes with heavy parameterization, leading to external dynamic random-access memory (DRAM) for storage. The prohibitive energy of DRAM accesses makes it non-trivial to deploy DNN on resource-constrained devices, calling for minimizing the weight and data movements to improve the energy efficiency. We present SmartDeal (SD), an algorithm framework to trade higher-cost memory storage/access for lower-cost computation, in order to aggressively boost the storage and energy efficiency, for both inference and training. The core of SD is a novel weight decomposition with structural constraints, carefully crafted to unleash the hardware efficiency potential. Specifically, we decompose each weight tensor as the product of a small basis matrix and a large structurally sparse coefficient matrix whose non-zeros are quantized to power-of-2. The resulting sparse and quantized DNNs enjoy greatly reduced energy for data movement and weight storage, incurring minimal overhead to recover the original weights thanks to the sparse bit-operations and cost-favorable computations. Beyond inference, we take another leap to embrace energy-efficient training, introducing innovative techniques to address the unique roadblocks arising in training while preserving the SD structures. We also design a dedicated hardware accelerator to fully utilize the SD structure to improve the real energy efficiency and latency. We conduct experiments on both multiple tasks, models and datasets in different settings. Results show that: 1) applied to inference, SD achieves up to 2.44x energy efficiency as evaluated via real hardware implementations; 2) applied to training, SD leads to 10.56x and 4.48x reduction in the storage and training energy, with negligible accuracy loss compared to state-of-the-art training baselines. Our source codes are available online.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. Every once in a while, it's crucial to step back from the immediate mess and gossip and all the little things we tend to focus on each day to look at our world from a 30,000-foot view, to project what we should expect moving forward. As we enter a new decade, this seems like the perfect time to think about and prepare for what may come over the next 10 years both at home and abroad. To state the obvious, this is not an exact science.

Open-domain Question Answering (OpenQA) is an important task in Natural Language Processing (NLP), which aims to answer a question in the form of natural language based on large-scale unstructured documents. Recently, there has been a surge in the amount of research literature on OpenQA, particularly on techniques that integrate with neural Machine Reading Comprehension (MRC). While these research works have advanced performance to new heights on benchmark datasets, they have been rarely covered in existing surveys on QA systems. In this work, we review the latest research trends in OpenQA, with particular attention to systems that incorporate neural MRC techniques. Specifically, we begin with revisiting the origin and development of OpenQA systems. We then introduce modern OpenQA architecture named ``Retriever-Reader'' and analyze the various systems that follow this architecture as well as the specific techniques adopted in each of the components. We then discuss key challenges to developing OpenQA systems and offer an analysis of benchmarks that are commonly used. We hope our work would enable researchers to be informed of the recent advancement and also the open challenges in OpenQA research, so as to stimulate further progress in this field.