A visual embedding for the unsupervised extraction of abstract semantics

Vector-space word representations obtained from neural network models have been shown to enable semantic operations based on vector arithmetic. In this paper, we explore the existence of similar information on vector representations of images. For that purpose we define a methodology to obtain large, sparse vector representations of image classes, and generate vectors through the state-of-the-art deep learning architecture GoogLeNet for 20 K images obtained from ImageNet. We first evaluate the resultant vector-space semantics through its correlation with WordNet distances, and find vector distances to be strongly correlated with linguistic semantics. We then explore the location of images within the vector space, finding elements close in WordNet to be clustered together, regardless of significant visual variances (e.g., 118 dog types). More surprisingly, we find that the space unsupervisedly separates complex classes without prior knowledge (e.g., living things). Afterwards, we consider vector arithmetics. Although we are unable to obtain meaningful results on this regard, we discuss the various problem we encountered, and how we consider to solve them. Finally, we discuss the impact of our research for cognitive systems, focusing on the role of the architecture being used.     

Fuzzy system for intelligent word recognition using a regular grammar

We present a new approach for off-line intelligent word recognition based on a fuzzy classification model. First, we segment a word into its single characters, and label each pixel as vertical or as horizontal so that we can group all the pixels into vertical or horizontal strokes. Then, we use dynamic zoning to obtain the locations of the connections between the vertical strokes – which are the main strokes – and the horizontal ones. These features let us construct the representative string of a character using a regular grammar and, subsequently, use a Deterministic Finite Automaton to check them out. To accomplish the recognition, we use a Fuzzy Lattice Reasoning classifier. The combination of the representative strings and the fuzzy classifier provides promising performance rates.     

Exploratory study of the effect of binaural beat stimulation on the EEG activity pattern in resting state using artificial neural networks

Anxiety disorders afflict almost 7.3 percent of the world’s population. One in 14 people will experience anxiety disorder at the given year. When associated with mood disorders, anxiety can also trigger or increase other diseases’ symptoms and effects, like depression and suicidal behavior. Binaural beats are a low-frequency type of acoustic stimulation perceived when the individual is subjected to two slightly different wave frequencies, from 200 to 900 Hz. Binaural beats can contribute to anxiety reduction and modification of other psychological conditions and states, modifying cognitive processes and mood states. In this work, we applied a 5 Hz binaural beat to 6 different subjects, to detect a relevant change in their brainwaves before and after the stimuli. We applied 20 min stimuli in 10 separated sessions. We assessed the differences using a Multi-Layer Perceptron classifier in comparison with non-parametric tests and Low-Resolution Brain Electromagnetic Tomography (eLORETA). eLORETA showed remarkable changes in High Alpha. Both eLORETA and MLP approaches revealed outstanding modifications in high Beta. MLP evinced significant changes in Theta brainwaves. Our study evidenced high Alpha modulation at the limbic lobe, implicating in a possible reduction of sympathetic system activation in the studied sample. Our main results on eLORETA suggest a strong increase in the current distribution, mostly in Alpha 2, at the Anterior Cingulate, which is related to the monitoring of mistakes regarding social conduct, recognition and expression of emotions. We also found that MLPs are able of evincing the main differences with high separability in Delta and Theta.     

Brainwave classification without the help of limb movement and any stimulus for character-writing application

Recently, Brain-Computer Interfaces (BCIs) have been extensively popular for employing Electroencephalography (EEG) signals to control devices with different applications. The use of BCIs currently involves for lots of applications to help the disabilities who cannot communicate with other people, as it is an alternative way for communication by passing the need of speech. Although the applications to spell the character with BCI systems (e.g., P300-speller, SSVEP-speller, Hex-O-spell) have been already developed, but these techniques are not flexible in the real scenarios because they require the stimulus all the time or stopping the activity to focus on the limb movement in order to provide the accuracy of brain responses. In this paper, the feasibility of brainwave classification for the applications of character-writing by considering only the EEG signals without the need of stimulus unlike the literature is newly introduced. This paper adopts a classification technique named Artificial Neural Network (ANN) and focuses on two different characters; straight line and circle. From the experimental results, the suitable position of electrodes are the pair of electrodes (F3 and F4) at the frontal lobe, which provide the best result as compared to other areas due to its important role in perception, maintenance and revival of the information. The experimental results indicate that the classification accuracy of the proposed technique is about 70%, which in turn leads to a significant achievement for the development of character-writing applications.     

Winky Dink and Me: Origins

Through early childhood experiences and then recollections of the many cyberneticians he knew in the 1970s and 1980s, the author traces his personal trajectory toward interaction design and cybernetics. He moves from fascination with technology, through disillusionment about Artificial Intelligence, to seeing that living in cybernetics is a journey of return to uncertainty, risk, and possibility.     

Bigrams and the richness of the stimulus

Recent challenges to Chomsky's poverty of the stimulus thesis for language acquisition suggest that children's primary data may carry "indirect evidence" about linguistic constructions despite containing no instances of them. Indirect evidence is claimed to suffice for grammar acquisition, without need for innate knowledge. This article reports experiments based on those of Reali and Christiansen (2005) , who demonstrated that a simple bigram language model can induce the correct form of auxiliary inversion in certain complex questions. This article investigates the nature of the indirect evidence that supports this learning, and assesses how reliably it is available. Results confirm the original finding for one specific sentence type but show that the model's success is highly circumscribed. It performs poorly on inversion in related constructions in English and Dutch. Because other, more powerful statistical models have so far been shown to succeed only on the same limited subset of cases as the bigram model, it remains to be seen whether stimulus richness can be substantiated more generally.     

Modeling how, when, and what is learned in a simple fault-finding task

We have developed a process model that learns in multiple ways while finding faults in a simple control panel device. The model predicts human participants' learning through its own learning. The model's performance was systematically compared to human learning data, including the time course and specific sequence of learned behaviors. These comparisons show that the model accounts very well for measures such as problem-solving strategy, the relative difficulty of faults, and average fault-finding time. More important, because the model learns and transfers its learning across problems, it also accounts for the faster problem-solving times due to learning when examined across participants, across faults, and across the series of 20 trials on an individual participant basis. The model shows how learning while problem solving can lead to more recognition-based performance, and helps explain how the shape of the learning curve can arise through learning and be modified by differential transfer. Overall, the quality of the correspondence appears to have arisen from procedural, declarative, and episodic learning all taking place within individual problem-solving episodes.     

Infinitary Action Logic: Complexity, Models and Grammars

Action logic of Pratt [21] can be presented as Full Lambek Calculus FL [14, 17] enriched with Kleene star *; it is equivalent to the equational theory of residuated Kleene algebras (lattices). Some results on axiom systems, complexity and models of this logic were obtained in [4, 3, 18]. Here we prove a stronger form of *-elimination for the logic of *-continuous action lattices and the –completeness of the equational theories of action lattices of subsets of a finite monoid and action lattices of binary relations on a finite universe. We also discuss possible applications in linguistics. Presented by Jacek Malinowski     

内隐学习中的知识习得及其无意识性测量*

本研究采用经典的人工语法范式,并引入迁移任务探讨在记忆和规则探索两种指导语条件下,被试所习得的究竟是规则还是组块？同时采用结构知识主观测量的方法,对内隐学习习得知识的无意识性进行测量。结果发现记忆指导语条件下的被试能成功区分合法串和非法串,即出现语法学习效应,但规则探索指导语条件下的被试并没有表现出语法或组块学习效应,结构知识的主观测量发现这种内隐学习的优势效应主要来自无意识结构知识的贡献;在迁移研究中发现附带学习组和有意学习组均在迁移任务上表现出语法学习效应,这表明在人工语法学习中所获得的语法规则是抽象的和可迁移的。     

Intergenerational influence and ontogenetic development in the emergence of spatial grammar in Nicaraguan Sign Language

The recent emergence of a new sign language among deaf children and adolescents in Nicaragua provides an opportunity to study how grammatical features of a language arise and spread, and how new language environments are constructed. The grammatical regularities that underlie language use reside largely outside the domain of explicit awareness. Nevertheless, knowledge of these regularities must be transmitted from one generation to the next to survive as part of the language. During this transmission, language form and use is shaped by both the characteristics of ontogenetic development within individual users and by historical changes in patterns of interaction between users. To capture this process, the present study follows the emergence of spatial modulations in Nicaraguan Sign Language (NSL). A comprehension task examining interpretations of spatially modulated verbs reveals that new form-function mappings arise among children who functionally differentiate previously equivalent forms. The new mappings are then acquired by their age peers (who are also children), and by subsequent generations of children who learn the language, but not by adult contemporaries. As a result, language emergence is characterized by a convergence on form within each age cohort, and a mismatch in form from one age cohort to the cohort that follows. In this way, each age cohort, in sequence, transforms the language environment for the next, enabling each new cohort of learners to develop further than its predecessors.