Just as humans can draw conclusions responsibly or irresponsibly, so too can computers. Machine learning systems that have been trained on data sets that include irresponsible judgments are likely to yield irresponsible predictions as outputs. In this paper I focus on a particular kind of inference a computer system might make: identification of the intentions with which a person acted on the basis of photographic evidence. Such inferences are liable to be morally objectionable, because of a way in which (...) they are presumptuous. After elaborating this moral concern, I explore the possibility that carefully procuring the training data for image recognition systems could ensure that the systems avoid the problem. The lesson of this paper extends beyond just the particular case of image recognition systems and the challenge of responsibly identifying a person’s intentions. Reflection on this particular case demonstrates the importance (as well as the difficulty) of evaluating machine learning systems and their training data from the standpoint of moral considerations that are not encompassed by ordinary assessments of predictive accuracy. (shrink)

Previous research on associative learning has uncovered detailed aspects of the process, including what types of things are learned, how they are learned, and where in the brain such learning occurs. However, perceptual processes, such as stimulus recognition and identification, take time to unfold. Previous studies of learning have not addressed when, during the course of these dynamic recognition processes, learned representations are formed and updated. If learned representations are formed and updated while recognition is ongoing, the (...) result of learning may incorporate spurious, partial information. For example, during word recognition, words take time to be identified, and competing words are often active in parallel. If learning proceeds before this competition resolves, representations may be influenced by the preliminary activations present at the time of learning. In three experiments using word learning as a model domain, we provide evidence that learning reflects the ongoing dynamics of auditory and visual processing during a learning event. These results show that learning can occur before stimulus recognition processes are complete; learning does not wait for ongoing perceptual processing to complete. (shrink)

Native and to some extent non-native speakers have shown processing advantages for idioms compared to novel literal phrases, and there is limited evidence that this advantage also extends to memory in L1 children. This study investigated whether these advantages generalize to recognition memory in adults. It employed a learning paradigm to test whether there is a recognition memory advantage for idioms compared to literal phrases in adult L1 and L2 learners considering both form and meaning recognition. Additionally, we asked (...) whether the presence of unfamiliar vocabulary interferes with phrasal learning by looking at recall of such unfamiliar words. When encountering new idioms, L2 learners often must cope with both figurative meaning and unfamiliar vocabulary. While single word meaning need not interfere with idiomatic meaning, it is a building block for the meaning of literal phrases. In Experiment 1, L2 learners showed equal recall for the form and meaning of literal and idiomatic phrases in which either all words were highly familiar, or one word was unfamiliar. However, unfamiliar words decreased overall recognition and were also remembered significantly better in literal compared to idiomatic phrases. In Experiment 2, L1 speakers also showed no recall differences between phrase types, but they displayed a trending increase in recognition in the presence of unfamiliar words. We conclude that there is no inherent recognition memory advantage for idioms based on figurativeness alone, and word- and phrasal meaning interact differently in learner groups. (shrink)

How does the visual system recognize images of a novel object after a single observation despite possible variations in the viewpoint of that object relative to the observer? One possibility is comparing the image with a prototype for invariance over a relevant transformation set. However, invariance over rotations has proven difficult to analyze, because it applies to some objects but not others. We propose that the invariant transformations of an object are learned by incorporating prior expectations with real-world evidence. We (...) test this proposal by developing an ideal learner model for learning invariance that predicts better learning of orientation dependence when prior expectations about orientation are weak. This prediction was supported in two behavioral experiments, where participants learned the orientation dependence of novel images using feedback from solving arithmetic problems. (shrink)

In the recent years, gesture recognition based on the surface electromyography (sEMG) signals has been extensively studied. However, the accuracy and stability of gesture recognition through traditional machine learning algorithms are still insufficient to some actual application scenarios. To enhance this situation, this paper proposed a method combining feature selection and ensemble extreme learning machine (EELM) to improve the recognition performance based on sEMG signals. First, the input sEMG signals are preprocessed and 16 features are then extracted from (...) each channel. Next, features that mostly contribute to the gesture recognition are selected from the extracted features using the recursive feature elimination (RFE) algorithm. Then, several independent ELM base classifiers are established using the selected features. Finally, the recognition results are determined by integrating the results obtained by ELM base classifiers using the majority voting method. The Ninapro DB5 dataset containing 52 different hand movements captured from 10 able-bodied subjects was used to evaluate the performance of the proposed method. The results showed that the proposed method could perform the best (overall average accuracy 77.9%) compared with decision tree (DT), ELM, and random forest (RF) methods. (shrink)

Tactile emotion recognition provides a lot of valuable information in human-computer interaction, and it has strong application prospects in many aspects such as smart home and medical treatment. So this situation raises a question: How to quickly and efficiently let the robot perform the correct emotion recognition? In this work, we develop a lifelong learning algorithm which is based on the efficient dictionary learning technology, to tackle the tactile emotion recognition across different tasks. To verify the efficiency of (...) the proposed method, we applied it to two data sets for experimentation: Corpus of Social Touch (CoST) and our dataset(We built it with a 12X12 array sensor). The results show that the proposed lifelong learning algorithm achieves satisfactory results. (shrink)

Contrary to the outstanding simplistic view of the taste system, learning studies show a more complex picture. Behavioral data using conditioned taste preference and aversion tasks support the idea that mixtures involve complex interactions between individual taste cues. Evidence from taste conditioned blocking, taste perceptual learning, and taste learned preferences is considered to support such a view. Greater support for research in taste learning and memory is required for a complete understanding of taste recognition.

In this paper, we propose to incorporate the local attention in WaveNet-CTC to improve the performance of Tibetan speech recognition in multitask learning. With an increase in task number, such as simultaneous Tibetan speech content recognition, dialect identification, and speaker recognition, the accuracy rate of a single WaveNet-CTC decreases on speech recognition. Inspired by the attention mechanism, we introduce the local attention to automatically tune the weights of feature frames in a window and pay different attention on context information (...) for multitask learning. The experimental results show that our method improves the accuracies of speech recognition for all Tibetan dialects in three-task learning, compared with the baseline model. Furthermore, our method significantly improves the accuracy for low-resource dialect by 5.11% against the specific-dialect model. (shrink)

ABSTRACTThe six basic emotions have long been considered discrete categories that serve as the primary units of the emotion system. Yet recent evidence indicated underlying connections among them. Here we tested the underlying relationships among the six basic emotions using a perceptual learning procedure. This technique has the potential of causally changing participants’ emotion detection ability. We found that training on detecting a facial expression improved the performance not only on the trained expression but also on other expressions. Such (...) a transfer effect was consistently demonstrated between disgust and anger detection as well as between fear and surprise detection in two experiments. Notably, training on any of the six emotions could improve happiness detection, while sadness detection could only be improved by training on sadness itself, suggesting the uniqueness of happiness and sadness.... (shrink)

This exploration aims to study the emotion recognition of speech and graphic visualization of expressions of learners under the intelligent learning environment of the Internet. After comparing the performance of several neural network algorithms related to deep learning, an improved convolution neural network-Bi-directional Long Short-Term Memory algorithm is proposed, and a simulation experiment is conducted to verify the performance of this algorithm. The experimental results indicate that the Accuracy of CNN-BiLSTM algorithm reported here reaches 98.75%, which is at (...) least 3.15% higher than that of other algorithms. Besides, the Recall is at least 7.13% higher than that of other algorithms, and the recognition rate is not less than 90%. Evidently, the improved CNN-BiLSTM algorithm can achieve good recognition results, and provide significant experimental reference for research on learners’ emotion recognition and graphic visualization of expressions in an intelligent learning environment. (shrink)

Ballard et al.'s principle of deictic coding as exemplified in the analysis of fixation patterns relies on a functional dichotomy between foveal and extrafoveal vision based on the well-known dependency of spatial resolution on eccentricity. Experimental evidence suggests that for processes of pattern learning and recognition such a dichotomy may be less warranted because its manifestation depends on the learning state of the observer. This finding calls for an explicit consideration of learning mechanisms within deictic coding schemes.

This paper uses an improved deep learning algorithm to judge the rationality of the design of landscape image feature recognition. The preprocessing of the image is proposed to enhance the data. The deficiencies in landscape feature extraction are further addressed based on the new model. Then, the two-stage training method of the model is used to solve the problems of long training time and convergence difficulties in deep learning. Innovative methods for zoning and segmentation training of landscape pattern (...) features are proposed, which makes model training faster and generates more creative landscape patterns. Because of the impact of too many types of landscape elements in landscape images, traditional convolutional neural networks can no longer effectively solve this problem. On this basis, a fully convolutional neural network model is designed to perform semantic segmentation of landscape elements in landscape images. Through the method of deconvolution, the pixel-level semantic segmentation is realized. Compared with the 65% accuracy rate of the convolutional neural network, the fully convolutional neural network has an accuracy rate of 90.3% for the recognition of landscape elements. The method is effective, accurate, and intelligent for the classification of landscape element design, which better improves the accuracy of classification, greatly reduces the cost of landscape element design classification, and ensures that the technical method is feasible. This paper classifies landscape behavior based on this model for full convolutional neural network landscape images and demonstrates the effectiveness of using the model. In terms of landscape image processing, the image evaluation provides a certain basis. (shrink)

The recognition in electroencephalogram of action idea is to identify what action people want to do by EEG. The significance of this project is to help people who have trouble in movement. Their action ideas are identified by EEG, and then robot hands can assist them to complete the action. This paper, with comparative experiments, used OpenBCI to collect EEG action ideas during static action and dynamic action and used the EEG recognition model Conv1D-GRU to training and recognition action, respectively. (...) The experimental result shows that the brain wave action idea is easier to recognize in static state. The accuracy of brain wave action idea recognition in dynamic state is only 72.27%, and the accuracy of brain wave action idea recognition in static state is 99.98%. The experimental result confirms that the action idea will be of great help to people with mobility difficulties. (shrink)

The accurate recognition of speech is beneficial to the fields of machine translation and intelligent human–computer interaction. After briefly introducing speech recognition algorithms, this study proposed to recognize speech with a recurrent neural network (RNN) and adopted the connectionist temporal classification (CTC) algorithm to align input speech sequences and output text sequences forcibly. Simulation experiments compared the RNN-CTC algorithm with the Gaussian mixture model–hidden Markov model and convolutional neural network-CTC algorithms. The results demonstrated that the more training samples the speech (...) recognition algorithm had, the higher the recognition accuracy of the trained algorithm was, but the training time consumption increased gradually; the more samples a trained speech recognition algorithm had to test, the lower the recognition accuracy and the longer the testing time. The proposed RNN-CTC speech recognition algorithm always had the highest accuracy and the lowest training and testing time among the three algorithms when the number of training and testing samples was the same. (shrink)

Philosophers have often applied a distinctively epistemic framework to the question of how moral knowledge can be derived from fictional literature, by considering how true propositions, or their argumentative support, can be the cognitive fruits of reading works of fiction. I offer an alternative approach. I focus not on whether readers fail to assent to the truth of a proposition or fail to provide it rational support. Instead, I focus on how readers fail to accord a truth (which they already (...) accept) adequate importance in their web of beliefs about living a good human life. This is a form of ignorance, but in the form of neglect, or failure to pay proper regard – which is one sense of the term ‘forgetfulness’. I argue that works of fictional literature may, at times, stimulate audience members to overcome their own particular forms of forgetfulness in this respect. And I use Tolstoy’s The Death of Ivan Ilyich as a case in point. (shrink)

Previous studies suggest a relationship between second-language learning and voice recognition processes, but the nature of such relation remains poorly understood. The present study investigates whether phoneme learning relates to voice recognition. A group of bilinguals that varied in their discrimination of a second-language phoneme contrast participated in this study. We assessed participants’ voice recognition skills in their native language at the behavioral and brain electrophysiological levels during a voice-avatar learning paradigm. Second-language phoneme discrimination positively correlated with (...) behavioral and brain measures of voice recognition. At the electrophysiological level, correlations were present at two time windows and are interpreted within the dual-process model of recognition memory. The results are relevant to understanding the processes involved in language learning as they show a common variability for second-language phoneme and voice recognition processes. (shrink)

본고는 딥러닝의 이미지 인식 원리와 유아의 이미지 인식 원리를 종합하면서, 이미지-개념 학습을 위한 새로운 교수학습모델, 즉 “베이지안 구조구성주의 교수학습모델”(Bayesian Structure-constructivist Teaching-learning Model: BSTM)을 제안한다. 달리 말하면, 기계학습 원리와 인간학습 원리를 비교함으로써 얻게 되는 시너지 효과를 바탕으로, 유아들의 이미지-개념 학습을 위한 새로운 교수 모델을 구성하는 것을 목표로 한다. 이런 맥락에서 본고는 전체적으로 3가지 차원에서 논의된다. 첫째, 아동의 이미지 학습에 대한 역사적 중요 이론인 “대상 전체론적 가설”, “분류학적 가설”, “배타적 가설”, “기본 수준 범주 가설” 등을 역사 비판적 관점에서 검토한다. 둘째, 컴퓨터 (...) 공학에서 전개된 머신러닝의 이미지 학습 원리 및 그 구조의 역사적 변형들에 대해서 비판적으로 분석하면서, 특히 딥러닝의 교육 인식론적 의미를 도출한다. 셋째, 선행하는 논의들을 토대로 이미지와 개념을 연결시키는 학습, 즉 단어학습을 위한 필자의 고유한 이론인 구조구성주의 개념교수모델을 제안한다. 이때 필자는 피아제의 명제논리학적 학습 가설, 즉 논리-수학적 구조를 중시하는 기존의 피아제 학파의 학습 가설과 최근의 베이지안 학습 이론에서 강조된 확률론적 추론 가설, 특히 “교육학적 추론 가설”을 동시에 포함할 수 있는 교수학습모델의 구조 및 주요 지향점들을 제안한다. (shrink)

This is a case study of goldsmith craft apprenticeship learning and recognition. The study includes 13 participants in a goldsmith's workshop. The theoretical approach to recognition and learning is inspired by sociocultural theory. In this article recognition is defined with reference to Hegel’s understanding of the concept as a transformed struggle of granting acknowledgement to another person plus receiving acknowledgement as a person. It is argued that the notion of recognition can enhance sociocultural notions of learning. In (...) analysing the case study of apprenticeship learning, the article suggests that recognition is expressed in the act of participants staking their lives to prove their autonomy, in work activity in terms of the role of artefacts and in the form of abstract and concrete recognition. Finally recognition is discussed in relation to learning and development. The study concludes that recognition is an important category not only to explain apprenticeship learning but also to give a sociocultural explanation of learning in general. (shrink)

It is well known that the unpredictable speech production brought on by stress from the task at hand has a significant negative impact on the performance of speech processing algorithms. Speech therapy benefits from being able to detect stress in speech. Speech processing performance suffers noticeably when perceptually produced stress causes variations in speech production. Using the acoustic speech signal to objectively characterize speaker stress is one method for assessing production variances brought on by stress. Real-world complexity and ambiguity make (...) it difficult for decision-makers to express their conclusions with clarity in their speech. In particular, the Neutrosophic speech algorithm is used to encode the language variables because they cannot be computed directly. Neutrosophic sets are used to manage indeterminacy in a practical situation. Existing algorithms are used except for stress on Neutrosophic speech recognition. The creation of algorithms that calculate, categorize, or differentiate between different stress circumstances. Understanding stress and developing strategies to combat its effects on speech recognition and human-computer interaction system are the goals of this recognition. (shrink)