Deep learning models (aka neural nets) now power everything from self-driving cars to video recommendations on a YouTube feed, having grown very popular over the last couple of years. Despite their popularity, the technology is known to have some drawbacks, such as the deep learning "reproducibility crisis"-- as it is very common for researchers at one to be unable to recreate a set of results published by another, even on the same data set. Additionally, the steep costs of deep learning would give any company pause, as the FAANG companies have spent over $30,000 to train just a single (very) deep net. Even the largest tech companies on the planet struggle with the scale, depth, and complexity of venturing into neural nets, while the same problems are even more pronounced for smaller data science organizations as neural nets can be both time-and cost-prohibitive. Also, there is no guarantee that neural nets will be able to outperform benchmark models like logistic regression or gradient-boosted ones, as neural nets are finicky and typically require added data and engineering complexities.

In machine learning (ML), if the situation when the model does not generalize well from the training data to unseen data is called overfitting. As you might know, it is one of the trickiest obstacles in applied machine learning. The first step in tackling this problem is to actually know that your model is overfitting. That is where proper cross-validation comes in. After identifying the problem you can prevent it from happening by applying regularization or training with more data. Still, sometimes you might not have additional data to add to your initial dataset. Acquiring and labeling additional data points may also be the wrong path. Of course, in many cases, it will deliver better results, but in terms of work, it is time-consuming and expensive a lot of the time.

In recent years, large amounts of data have been generated, and computer power has kept growing. This scenario has led to a resurgence in the interest in artificial neural networks. One of the main challenges in training effective neural network models is finding the right combination of hyperparameters to be used. Indeed, the choice of an adequate approach to search the hyperparameter space directly influences the accuracy of the resulting neural network model. Common approaches for hyperparameter optimization are Grid Search, Random Search, and Bayesian Optimization. There are also population-based methods such as CMA-ES. In this paper, we present HBRKGA, a new population-based approach for hyperparameter optimization. HBRKGA is a hybrid approach that combines the Biased Random Key Genetic Algorithm with a Random Walk technique to search the hyperparameter space efficiently. Several computational experiments on eight different datasets were performed to assess the effectiveness of the proposed approach. Results showed that HBRKGA could find hyperparameter configurations that outperformed (in terms of predictive quality) the baseline methods in six out of eight datasets while showing a reasonable execution time.

Feature-based transfer is one of the most effective methodologies for transfer learning. Existing studies usually assume that the learned new feature representation is truly \emph{domain-invariant}, and thus directly train a transfer model $\mathcal{M}$ on source domain. In this paper, we consider a more realistic scenario where the new feature representation is suboptimal and small divergence still exists across domains. We propose a new learning strategy with a transfer model called Randomized Transferable Machine (RTM). More specifically, we work on source data with the new feature representation learned from existing feature-based transfer methods. The key idea is to enlarge source training data populations by randomly corrupting source data using some noises, and then train a transfer model $\widetilde{\mathcal{M}}$ that performs well on all the corrupted source data populations. In principle, the more corruptions are made, the higher the probability of the target data can be covered by the constructed source populations, and thus better transfer performance can be achieved by $\widetilde{\mathcal{M}}$. An ideal case is with infinite corruptions, which however is infeasible in reality. We develop a marginalized solution with linear regression model and dropout noise. With a marginalization trick, we can train an RTM that is equivalently to training using infinite source noisy populations without truly conducting any corruption. More importantly, such an RTM has a closed-form solution, which enables very fast and efficient training. Extensive experiments on various real-world transfer tasks show that RTM is a promising transfer model.

Recurrent neural networks are the basis of the state-of-the-art models in natural language processing, including language modeling (Mikolov et al., 2011), machine translation (Cho et al., 2014) and named entity recognition (Lample et al., 2016). It is needless to say that complex learning tasks require relatively large networks with millions of parameters to be accomplished. However, large neural networks need more data and/or strong regularization techniques to be trained successfully and avoid overfitting. Without the means to collect more data, which is the case in the majority of real-world problems, data augmentation and regularization methods are standard alternative practices to overcome this barrier. Data augmentation in natural language processing is limited, and often task-specific (Kobayashi, 2018; Kafle et al., 2017). On the other hand, adopting the same regularization methods that are originally proposed for feed-forward (non-recurrent) networks needs to be done with extra care to avoid hurting the network's information flow between consecutive time-steps. To overcome such limitations, we present Sequence Mixup: a set of training methods, regularization techniques, and data augmentation procedures for RNNs. Sequence Mixup can be considered as the RNN-generalization of input mixup (Zhang et al., 2017) and manifold mixup (Verma et al., 2018), which are already introduced for feed-forward neural

Social Networking Sites (SNS) are one of the most important ways of communication. In particular, microblogging sites are being used as analysis avenues due to their peculiarities (promptness, short texts...). There are countless researches that use SNS in novel manners, but machine learning (ML) has focused mainly in classification performance rather than interpretability and/or other goodness metrics. Thus, state-of-the-art models are black boxes that should not be used to solve problems that may have a social impact. When the problem requires transparency, it is necessary to build interpretable pipelines. Arguably, the most decisive component in the pipeline is the classifier, but it is not the only thing that we need to consider. Despite that the classifier may be interpretable, resulting models are too complex to be considered comprehensible, making it impossible for humans to comprehend the actual decisions. The purpose of this paper is to present a feature selection mechanism (the first step in the pipeline) that is able to improve comprehensibility by using less but more meaningful features while achieving a good performance in microblogging contexts where interpretability is mandatory. Moreover, we present a ranking method to evaluate features in terms of statistical relevance and bias. We conducted exhaustive tests with five different datasets in order to evaluate classification performance, generalisation capacity and actual interpretability of the model. Our results shows that our proposal is better and, by far, the most stable in terms of accuracy, generalisation and comprehensibility.

Recently, many plug-and-play self-attention modules are proposed to enhance the model generalization by exploiting the internal information of deep convolutional neural networks (CNNs). Previous works lay an emphasis on the design of attention module for specific functionality, e.g., light-weighted or task-oriented attention. However, they ignore the importance of where to plug in the attention module since they connect the modules individually with each block of the entire CNN backbone for granted, leading to incremental computational cost and number of parameters with the growth of network depth. Thus, we propose a framework called Efficient Attention Network (EAN) to improve the efficiency for the existing attention modules. In EAN, we leverage the sharing mechanism (Huang et al. 2020) to share the attention module within the backbone and search where to connect the shared attention module via reinforcement learning. Finally, we obtain the attention network with sparse connections between the backbone and modules, while (1) maintaining accuracy (2) reducing extra parameter increment and (3) accelerating inference. Extensive experiments on widely-used benchmarks and popular attention networks show the effectiveness of EAN. Furthermore, we empirically illustrate that our EAN has the capacity of transferring to other tasks and capturing the informative features. The code is available at https://github.com/gbup-group/EAN-efficient-attention-network

Multi-label image classification is the task of predicting a set of labels corresponding to objects, attributes or other entities present in an image. In this work we propose the Classification Transformer (C-Tran), a general framework for multi-label image classification that leverages Transformers to exploit the complex dependencies among visual features and labels. Our approach consists of a Transformer encoder trained to predict a set of target labels given an input set of masked labels, and visual features from a convolutional neural network. A key ingredient of our method is a label mask training objective that uses a ternary encoding scheme to represent the state of the labels as positive, negative, or unknown during training. Our model shows state-of-the-art performance on challenging datasets such as COCO and Visual Genome. Moreover, because our model explicitly represents the uncertainty of labels during training, it is more general by allowing us to produce improved results for images with partial or extra label annotations during inference. We demonstrate this additional capability in the COCO, Visual Genome, News500, and CUB image datasets.

Deep learning models such as Convolutional Neural Networks (CNNs) have demonstrated high levels of effectiveness in a variety of domains, including computer vision and more recently, computational biology. However, training effective models often requires assembling and/or labeling large datasets, which may be prohibitively time-consuming or costly. Pool-based active learning techniques have the potential to mitigate these issues, leveraging models trained on limited data to selectively query unlabeled data points from a pool in an attempt to expedite the learning process. Here we present "Dropout-based Expected IMprOvementS" (DEIMOS), a flexible and computationally-efficient approach to active learning that queries points that are expected to maximize the model's improvement across a representative sample of points. The proposed framework enables us to maintain a prediction covariance matrix capturing model uncertainty, and to dynamically update this matrix in order to generate diverse batches of points in the batch-mode setting. Our active learning results demonstrate that DEIMOS outperforms several existing baselines across multiple regression and classification tasks taken from computer vision and genomics.

Linking clinical narratives to standardized vocabularies and coding systems is a key component of unlocking the information in medical text for analysis. However, many domains of medical concepts lack well-developed terminologies that can support effective coding of medical text. We present a framework for developing natural language processing (NLP) technologies for automated coding of under-studied types of medical information, and demonstrate its applicability via a case study on physical mobility function. Mobility is a component of many health measures, from post-acute care and surgical outcomes to chronic frailty and disability, and is coded in the International Classification of Functioning, Disability, and Health (ICF). However, mobility and other types of functional activity remain under-studied in medical informatics, and neither the ICF nor commonly-used medical terminologies capture functional status terminology in practice. We investigated two data-driven paradigms, classification and candidate selection, to link narrative observations of mobility to standardized ICF codes, using a dataset of clinical narratives from physical therapy encounters. Recent advances in language modeling and word embedding were used as features for established machine learning models and a novel deep learning approach, achieving a macro F-1 score of 84% on linking mobility activity reports to ICF codes. Both classification and candidate selection approaches present distinct strengths for automated coding in under-studied domains, and we highlight that the combination of (i) a small annotated data set; (ii) expert definitions of codes of interest; and (iii) a representative text corpus is sufficient to produce high-performing automated coding systems. This study has implications for the ongoing growth of NLP tools for a variety of specialized applications in clinical care and research.