We know in neural networks, neurons work with corresponding weight, bias and their respective activation functions. The weights get multiplied with the inputs and then activation function is applied to the element before going to the next layer. Finally, we get the predicted value (yhat) through the output layer. But prediction is always closer to the actual (y), which we term as errors. So, we define the loss/cost functions to capture the errors and try to optimize it though backpropagation.

The original Pointer Networks paper[1] was originally accepted to NeurIPS 2015, making it quite old in deep learning years. Nonetheless, it has amassed over 1700 citations to date and continues to be integrated into modern solutions[2, 3], has received many improvements [4, 5], and has inspired alternative architectures[6]. It even plays a small, but important role in a state-of-the-art model for playing StarCraft II created by Tencent AI Lab [7]. What is it about pointer networks that makes them so applicable even today? This simple and elegant architecture addresses a subtle complication in sequence prediction problems.

This entry is a part of the NYU Center for Data Science blog's recurring guest editorial series. Irina Espejo Morales is a CDS Ph.D. student in data science and also a DeepMind fellow. Kyle Cranmer is a CDS professor of data science and professor of physics at the NYU College of Arts & Science. Lukas Heinrich is a staff scientist at CERN working with the ATLAS experiment at the LHC and former NYU graduate student. Gilles Louppe is an associate professor in artificial intelligence and deep learning at the University of Liège (Belgium) and former Moore Sloan fellow.

In this paper, we propose a max-min entropy framework for reinforcement learning (RL) to overcome the limitation of the maximum entropy RL framework in model-free sample-based learning. Whereas the maximum entropy RL framework guides learning for policies to reach states with high entropy in the future, the proposed max-min entropy framework aims to learn to visit states with low entropy and maximize the entropy of these low-entropy states to promote exploration. For general Markov decision processes (MDPs), an efficient algorithm is constructed under the proposed max-min entropy framework based on disentanglement of exploration and exploitation. Numerical results show that the proposed algorithm yields drastic performance improvement over the current state-of-the-art RL algorithms.

We present TNCR, a new table dataset with varying image quality collected from free websites. The TNCR dataset can be used for table detection in scanned document images and their classification into 5 different classes. TNCR contains 9428 high-quality labeled images. In this paper, we have implemented state-of-the-art deep learning-based methods for table detection to create several strong baselines. Cascade Mask R-CNN with ResNeXt-101-64x4d Backbone Network achieves the highest performance compared to other methods with a precision of 79.7%, recall of 89.8%, and f1 score of 84.4% on the TNCR dataset. We have made TNCR open source in the hope of encouraging more deep learning approaches to table detection, classification, and structure recognition. The dataset and trained model checkpoints are available at https://github.com/abdoelsayed2016/TNCR_Dataset.

For example, a "what" concept is "where"-invariant and a "where" concept is "what"-invariant, as explained in [55], [68]. Section IV discusses an optimal framework through which such abstractions can take place from learning simple rules during early life that enable learning of more complex rules during later life-- called scaffolding [69]. Theorem 2 leads to two observations on data fitting on a static data set: Observation 1: Any data fitting on a static data set without learning invariant concepts are nonscalable, including the n-fold cross-validation discussed below. Unfortunately, data fitting on a static data set is a norm in all ImageNet Contests [66]. Namely, the remaining subsections in this section analyze approaches that are nonscalable. For example, computer vision is not a "one-shot" pattern classification problem as argued by Li Fei-Fei et al. [19] (which was questioned in PubMed without responses), but rather a spatiotemporal problem to learn various invariant concepts present in cluttered natural scenes through autonomous attention saccades, as explained further in Observation 2. Observation 2: Learning invariant concepts seem nonscalable for any data fitting on a static data set either, because there are too many images to be labeled by hand (e.g., all pixel locations) [55], [68]. Like a human baby, any scalable machine learning methods must be conscious through which the machine learner must consciously guess concepts (i.e., not just active learning [70]) (e.g., an object type) and verify their invariance rules (e.g., the where-invariance of a what concept).

Despite their widespread success, the application of deep neural networks to functional data remains scarce today. The infinite dimensionality of functional data means standard learning algorithms can be applied only after appropriate dimension reduction, typically achieved via basis expansions. Currently, these bases are chosen a priori without the information for the task at hand and thus may not be effective for the designated task. We instead propose to adaptively learn these bases in an end-to-end fashion. We introduce neural networks that employ a new Basis Layer whose hidden units are each basis functions themselves implemented as a micro neural network. Our architecture learns to apply parsimonious dimension reduction to functional inputs that focuses only on information relevant to the target rather than irrelevant variation in the input function. Across numerous classification/regression tasks with functional data, our method empirically outperforms other types of neural networks, and we prove that our approach is statistically consistent with low generalization error. Code is available at: \url{https://github.com/jwyyy/AdaFNN}.

A table arranging data in rows and columns is a very effective data structure, which has been widely used in business and scientific research. Considering large-scale tabular data in online and offline documents, automatic table recognition has attracted increasing attention from the document analysis community. Though human can easily understand the structure of tables, it remains a challenge for machines to understand that, especially due to a variety of different table layouts and styles. Existing methods usually model a table as either the markup sequence or the adjacency matrix between different table cells, failing to address the importance of the logical location of table cells, e.g., a cell is located in the first row and the second column of the table. In this paper, we reformulate the problem of table structure recognition as the table graph reconstruction, and propose an end-to-end trainable table graph reconstruction network (TGRNet) for table structure recognition. Specifically, the proposed method has two main branches, a cell detection branch and a cell logical location branch, to jointly predict the spatial location and the logical location of different cells. Experimental results on three popular table recognition datasets and a new dataset with table graph annotations (TableGraph-350K) demonstrate the effectiveness of the proposed TGRNet for table structure recognition. Code and annotations will be made publicly available.

Electromyography is a promising approach to the gesture recognition of humans if an efficient classifier with high accuracy is available. In this paper, we propose to utilize Extreme Value Machine (EVM) as a high-performance algorithm for the classification of EMG signals. We employ reflection coefficients obtained from an Autoregressive (AR) model to train a set of classifiers. Our experimental results indicate that EVM has better accuracy in comparison to the conventional classifiers approved in the literature based on K-Nearest Neighbors (KNN) and Support Vector Machine (SVM).

Existing pre-trained models for knowledge-graph-to-text (KG-to-text) generation simply fine-tune text-to-text pre-trained models such as BART or T5 on KG-to-text datasets, which largely ignore the graph structure during encoding and lack elaborate pre-training tasks to explicitly model graph-text alignments. To tackle these problems, we propose a graph-text joint representation learning model called JointGT. During encoding, we devise a structure-aware semantic aggregation module which is plugged into each Transformer layer to preserve the graph structure. Furthermore, we propose three new pre-training tasks to explicitly enhance the graph-text alignment including respective text / graph reconstruction, and graph-text alignment in the embedding space via Optimal Transport. Experiments show that JointGT obtains new state-of-the-art performance on various KG-to-text datasets.