Great Tits Learn Odors and Colors Equally Well, and Show No Predisposition for Herbivore-Induced Plant Volatiles

Ability to efficiently localize productive foraging habitat is crucial for nesting success of insectivorous birds. Some bird species can use olfaction to identify caterpillar-infested trees by detection of herbivore induced plant volatiles (HIPVs), but these cues probably need to be learned. So far, we know very little about the process of olfactory learning in birds, whether insectivorous species have a predisposition for detecting and learning HIPVs, due to the high ecological significance of these odors, and how olfaction is integrated with vision in making foraging decisions. In a standardized setup, we tested whether 35 wild-caught great tits (Parus major) show any preference for widely abundant HIPVs compared to neutral (non-induced) plant odors, how fast they learn to associate olfactory, visual and multimodal foraging cues with food, and whether the olfactory preferences and learning speed were influenced by bird sex or habitat (urban or rural). We also tested how fast birds switch to a new cue of the same modality. Great tits showed no initial preference for HIPVs compared to neutral odors, and they learned all olfactory cues at a similar pace, except for methyl salicylate (MeSA), which they learned more slowly. We also found no differences in learning speeds between visual, olfactory and multimodal foraging cues, but birds learned the second cue they were offered faster than the first one. Bird sex or habitat had no effect on learning speed or olfactory preference, but urban birds tended to learn visual cues more slowly. We conclude that insectivorous birds utilize olfactory and visual cues with similar efficiency in foraging, and that they probably don‘t have any special predisposition toward the tested HIPVs. These results confirm that great tits are flexible foragers with good learning abilities.

Prediction Of Myers-Briggs Type Indicator Personality Using Long Short-Term Memory

Personality is defined as the mix of features and qualities that make up an individual's particular character, including thoughts, feelings, and behaviors. With the rapid development of technology, personality computing is becoming a popular research field by providing users with personalization. Many researchers have used social media data to automatically predict personality. This research uses a public dataset from Kaggle, namely the Myers-Briggs Personality Type Dataset. The purpose of this study is to predict the accuracy and F1-score values so that the performance for predicting and classifying Myers–Briggs Type Indicator (MBTI) personality can work optimally by using attributes from the MBTI dataset, namely posts and types. Predictive accuracy analysis was carried out using the Long Short-Term Memory (LSTM) algorithm with random oversampling technique with the Imblearn library for MBTI personality type prediction and comparing the performance of the method proposed in this study with other popular machine learning algorithms. Experiments show that the LSTM model using the RMSprop optimizer and learning speed of 10-3 provides higher performance in terms of accuracy while for the F1-score the LSTM model using the RMSprop Optimizer and learning speed of 10-2 gives a higher value than the proposed machine learning algorithm so that the model MBTI dataset using LSTM with random oversampling can help in identifying the MBTI personality type.

Comparison of classical machine learning algorithms in the task of handwritten digits classification

The purpose of this paper is to compare classical machine learning algorithms for handwritten number classification. The following algorithms were chosen for comparison: Logistic Regression, SVM, Decision Tree, Random Forest and k-NN. MNIST handwritten digit database is used in the task of training and testing the above algorithms. The dataset consists of 70,000 images of numbers from 0 to 9. The algorithms are compared considering such criteria as the learning speed, prediction construction speed, host machine load, and classification accuracy. Each algorithm went through the training and testing phases 100 times, with the desired KPIs retained at each iteration. The results were averaged to reach reliable outcomes.

Lubricating culture awareness and critical thinking through humour

There is an ample evidence supporting the benefits of instructional humour, among which increased attention and interest, information retention and learning speed, more productive learning environment, a more positive image of the instructor, more efficient acquisition of linguistic and cultural competencies, an increased conversational involvement, enhanced cultural awareness and more stimulated critical thinking. However, most of the research findings rely on what is termed appropriate humor such as puns, jokes, anecdotes and alike, while potentially offensive humour that relates to sexual, ethnic, religious, political identity is generally labeled inappropriate and advised to be avoided in the classroom environment. It is in this particular context that this study seeks to test the potential of such humour, sexual and ethnic in particular, to act as a tool of increasing cultural awareness and stimulate critical thinking among university students. To do so, the study relies on an experimental class design combining few in-class and extracurricular activities created by using sexual and ethnic humour samples.

Matrix Neo-Fuzzy-System and its Online Learning in Image Recognition Task

The paper proposes a 2D-hybrid system of computational intelligence, which is based on the generalized neo-fuzzy neuron. The system is characterised by high approximate abilities, simple computational implementation, and high learning speed. The characteristic property of the proposed system is that on its input the signal is fed not in the traditional vector form, but in the image-matrix form. Such an approach allows getting rid of additional convolution-pooling layers that are used in deep neural networks as an encoder. The main elements of the proposed system are a fuzzified multidimensional bilinear model, additional softmax layer, and multidimensional generalized neo-fuzzy neuron tuning with cross-entropy criterion. Compared to deep neural systems, the proposed matrix neo-fuzzy system contains gradually fewer tuning parameters – synaptic weights. The usage of the time-optimal algorithm for tuning synaptic weights allows implementing learning in an online mode.

PERBANDINGAN METODE SEASONAL ARIMA DAN EXTREME LEARNING MACHINE PADA PERAMALAN JUMLAH WISATAWAN MANCANEGARA KE BALI

Bali Island of the Gods is one of the wealth of very popular tourist destinations and has the highest number of foreign tourists in Indonesia. It is very necessary to do more in-depth learning related to the projections or forecasting of foreign tourist visits to Bali at a certain period of time. Forecasting analysis used is to compare two methods, namely the Seasonal ARIMA method (SARIMA) and Extreme Learning Machine (ELM). The SARIMA method is a statistical method commonly used in forecasting time series data that contains seasonality and has good accuracy. While the ELM method is a new learning method of artificial neural networks that has fast learning speed and good accuracy. The results obtained indicate that the Seasonal ARIMA method is a better method used to predict the number of tourists to Bali in this case, because it has a smaller forecasting MAPE value of 4.97%. While the ELM method has a forecasting MAPE value of 7.62%.

Analysis of the deployment strategies of reinforcement learning controllers for complex dynamic systems

This paper benchmarks several strategies for deploying reinforcement learning (RL)-based controllers on heterogeneous hybrid systems. Sample inefficiency is often a significant cost for RL controllers because we need sufficient data to train them, and the controllers may take time to converge to an acceptable control policy. This can be doubly costly if system health is degrading, or if the network of such systems in turn cannot afford a gradually improving controller in its constituents. Learning speed improvement can be achieved via transfer learning across controllers trained on different tasks: simulations, data-driven models, or separate instances of similar systems. This paper discusses near- and far- transfers across tasks of varying similarities. These approaches are applied on a test-bed of models of cooling towers operating on office and residential buildings on a university campus.

Finder-MCTS: A Cognitive Spectrum Allocation Based on Traveling State Priority and Scenario Simulation in IoV

With the increasing number of intelligent connected vehicles, the problem of scarcity of communication resources has become increasingly obvious. It is a practical issue with important significance to explore a real-time and reliable dynamic spectrum allocation scheme for the vehicle users, while improving the utilization of the available spectrum. However, previous studies have problems such as local optimum, complex parameter setting, learning speed, and poor convergence. Thus, in this paper, we propose a cognitive spectrum allocation method based on traveling state priority and scenario simulation in IoV, named Finder-MCTS. The proposed method integrates offline learning with online search. This method mainly consists of two stages. Initially, Finder-MCTS gives the allocation priority of different vehicle users based on the vehicle’s local driving status and global communication status. Furthermore, Finder-MCTS can search for the approximate optimal allocation solutions quickly online according to the priority and the scenario simulation, while with the offline deep neural network-based environmental state predictor. In the experiment, we use SUMO to simulate the real traffic flows. Numerical results show that our proposed Finder-MCTS has 36.47%, 18.24%, and 9.00% improvement on average than other popular methods in convergence time, link capacity, and channel utilization, respectively. In addition, we verified the effectiveness and advantages of Finder-MCTS compared with two MCTS algorithms’ variations.

Correcting the Hebbian Mistake: Toward a Fully Error-Driven Hippocampus

The hippocampus plays a critical role in the rapid learning of new episodic memories. Many computational models propose that the hippocampus is an autoassociator that relies on Hebbian learning (i.e., "cells that fire together, wire together"). However, Hebbian learning is computationally suboptimal as it modifies weights unnecessarily beyond what is actually needed to achieve effective retrieval, causing more interference and resulting in a lower learning capacity. Our previous computational models have utilized a powerful, biologically plausible form of error-driven learning in hippocampal CA1 and entorhinal cortex (EC) (functioning as a sparse autoencoder) by contrasting local activity states at different phases in the theta cycle. Based on specific neural data and a recent abstract computational model, we propose a new model called Theremin (Total Hippocampal ERror MINimization) that extends error-driven learning to area CA3 --- the mnemonic heart of the hippocampal system. In the model, CA3 responds to the EC monosynaptic input prior to the EC disynaptic input through dentate gyrus (DG), giving rise to a temporal difference between these two activation states, which drives error-driven learning in the EC->CA3 and CA3<->CA3 projections. In effect, DG serves as a teacher to CA3, correcting its patterns into more pattern-separated ones, thereby reducing interference. Results showed that Theremin, compared with our original model, has significantly increased capacity and learning speed. The model makes several novel predictions that can be tested in future studies.