Linear Systems Theoretic Approach to Interpretation of Spatial and Temporal Weights in Compact CNNs: Monte-Carlo Study
Interpretation of the neural networks architectures for decoding the signals of the brain usually reduced to the analysis of spatial and temporal weights. We propose a theoretically justified method of their interpretation within the simple architecture based on a priori knowledge of the subject area. This architecture is comparable in decoding quality to the winner of the BCI IV competition and allows for automatic engineering of physiologically meaningful features. To demonstrate the operation of the algorithm, we performed Monte Carlo simulations and received a significant improvement in the restoration of patterns for different noise levels and also investigated the relation between the decoding quality and patterns reconstruction fidelity.
Drugs and diseases play a central role in many areas of biomedical research and healthcare. Aggregating knowledge about these entities across a broader range of domains and languages is critical for information extraction (IE) applications. To facilitate text mining methods for analysis and comparison of patient’s health conditions and adverse drug reactions reported on the Internet with traditional sources such as drug labels, we present a new corpus of Russian language health reviews.
The Russian Drug Reaction Corpus (RuDReC) is a new partially annotated corpus of consumer reviews in Russian about pharmaceutical products for the detection of health-related named entities and the effectiveness of pharmaceutical products. The corpus itself consists of two parts, the raw one and the labeled one. The raw part includes 1.4 million health-related user-generated texts collected from various Internet sources, including social media. The labeled part contains 500 consumer reviews about drug therapy with drug- and disease-related information. Labels for sentences include health-related issues or their absence. The sentences with one are additionally labeled at the expression level for identification of fine-grained subtypes such as drug classes and drug forms, drug indications and drug reactions. Further, we present a baseline model for named entity recognition (NER) and multilabel sentence classification tasks on this corpus. The macro F1 score of 74.85% in the NER task was achieved by our RuDR-BERT model. For the sentence classification task, our model achieves the macro F1 score of 68.82% gaining 7.47% over the score of BERT model trained on Russian data.
Brain computer interfaces are a growing research field producing many implementations that find various uses in research and medical practice and everyday life. Despite the popularity of the implementations using non-invasive neuroimaging methods, radical improvement in the state channel bandwidth and, thus, decoding accuracy is only possible by using invasive techniques. Electrocorticography (ECoG) is a minimally invasive neuroimaging modality that provides highly informative brain activity signals and entails the use of machine learning methods to efficiently decipher the complex spatial-temporal cortical representation of motor and cognitive function. Deep learning techniques is the family of machine learning methods that allow to learn representations of data with multiple levels of abstraction. We hypothesized that the deep learning would allow to reach higher accuracy in the task of decoding movement timecourse than it is possible with traditional signal processing approaches.
This book constitutes the refereed proceedings of the 11th International Conference on Intelligent Data Processing, IDP 2016, held in Barcelona, Spain, in October 2016.
The 11 revised full papers were carefully reviewed and selected from 52 submissions. The papers of this volume are organized in topical sections on machine learning theory with applications; intelligent data processing in life and social sciences; morphological and technological approaches to image analysis.
article deals with the problem of isolated words recognition based on deep convolutional neural networks. The use of existing recognition systems in practice is limited by an insufficiently high degree of their reliability functioning in conditions of intense acoustic noise, such as street noise, sounds from passing vehicles, etc. Nowadays, the most accurate recognition methods are characterized by the formation of acoustic models with deep learning technologies and, in particular, convolutional neural networks. For image processing problems the possibility of adaptation of such networks to a new domain with additional finetuning on rather small training samples is well studied. In this paper we proposed to perform additional training of networks for adaptation of acoustic models on a speaker voice with use of small number of the utterances. In order to reduce the error rate, we consider an ensemble of several different speaker-dependent neural network architectures that have been trained in such a way. The final decision is made by a weighted voting rule, in which the weight of each acoustic model is determined in proportion to the accuracy estimated on the training set. The experimental results for recognition of English commands proved that such ensemble of pre-trained acoustic models can significantly improve accuracy compared to traditional pre-trained models, especially if the white Gaussian noise is added to the input signal.
Recently, deep learning methods have been increasingly applied on spoken language technologies, including signal processing, language understanding and generation, dialogue management, as well as joint optimisations of these (end-to-end learning). However, such methods still have limitations and it is not yet clear that deep learning and joint optimisation is the key to the future.
Encompassing the current deep learning trends and traditional knowledge-based methods, SLT’s 2018 main theme will be around “Spoken Language Technology in the Era of Deep Learning: Challenges and Opportunities”.
The book presents a remarkable collection of chapters covering a wide range of topics in the areas of intelligent systems and artificial intelligence, and their real-world applications. It gathers the proceedings of the Intelligent Systems Conference 2019, which attracted a total of 546 submissions from pioneering researchers, scientists, industrial engineers, and students from all around the world. These submissions underwent a double-blind peer-review process, after which 190 were selected for inclusion in these proceedings.
As intelligent systems continue to replace and sometimes outperform human intelligence in decision-making processes, they have made it possible to tackle a host of problems more effectively. This branching out of computational intelligence in several directions and use of intelligent systems in everyday applications have created the need for an international conference as a venue for reporting on the latest innovations and trends.
This book collects both theory and application based chapters on virtually all aspects of artificial intelligence; presenting state-of-the-art intelligent methods and techniques for solving real-world problems, along with a vision for future research, it represents a unique and valuable asset.
Polar mesocyclones (MCs) are small marine atmospheric vortices. The class of intense MCs, called polar lows, are accompanied by extremely strong surface winds and heat fluxes and thus largely influencing deep ocean water formation in the polar regions. Accurate detection of polar mesocyclones in high-resolution satellite data, while challenging, is a time-consuming task, when performed manually. Existing algorithms for the automatic detection of polar mesocyclones are based on the conventional analysis of patterns of cloudiness and they involve different empirically defined thresholds of geophysical variables. As a result, various detection methods typically reveal very different results when applied to a single dataset. We develop a conceptually novel approach for the detection of MCs based on the use of deep convolutional neural networks (DCNNs). As a first step, we demonstrate that DCNN model is capable of performing binary classification of 500 × 500 km patches of satellite images regarding MC patterns presence in it. The training dataset is based on the reference database of MCs manually tracked in the Southern Hemisphere from satellite mosaics. We use a subset of this database with MC diameters falling in the range of 200–400 km. This dataset is further used for testing several different DCNN setups, specifically, DCNN built “from scratch”, DCNN based on VGG16 pre-trained weights also engaging the Transfer Learning technique, and DCNN based on VGG16 with Fine Tuning technique. Each of these networks is further applied to both infrared (IR) and a combination of infrared and water vapor (IR + WV) satellite imagery. The best skills (97% in terms of the binary classification accuracy score) is achieved with the model that averages the estimates of the ensemble of different DCNNs. The algorithm can be further extended to the automatic identification and tracking numerical scheme and applied to other atmospheric phenomena that are characterized by a distinct signature in satellite imagery.
Determining the tonality of the text is a difficult task, the solution of which essentially depends on the context, the field of study and the amount of text data. The analysis shows that the authors in their works do not jointly use the full range of possible transformations on the data and their combinations. The article explores a generalized approach, which consists in sequentially passing through the stages of intelligence analysis, obtaining a basic solution, vectorization, preprocessing, tuning hyperparameters and modeling. The experiments carried out by iterative application of these stages give a positive increase in quality for classical machine learning algorithms and a significant increase for deep learning.