scholarly journals THE IMPACT OF RESIDUAL LAYERS AND INCEPTION MODULES ON META-LEARNING

2020 ◽  
Vol 13(62) (1) ◽  
pp. 27-34
Author(s):  
L. Bularca ◽  
Keyword(s):  
Meta Learning ◽  
The Impact

scholarly journals Constructing Multiple Tasks for Augmentation: Improving Neural Image Classification with K-Means Features

2020 ◽  
Vol 34 (07) ◽  
pp. 10877-10884
Author(s):  
Tao Gui ◽  
Lizhi Qing ◽  
Qi Zhang ◽  
Jiacheng Ye ◽  
Hang Yan ◽  
...  
Keyword(s):  
Data Augmentation ◽  
Learning Approach ◽  
Main Task ◽  
Single Task ◽  
Task Learning ◽  
Multiple Tasks ◽  
Meta Learning ◽  
Meta Optimization ◽  
The Impact ◽  
Human Specific

Multi-task learning (MTL) has received considerable attention, and numerous deep learning applications benefit from MTL with multiple objectives. However, constructing multiple related tasks is difficult, and sometimes only a single task is available for training in a dataset. To tackle this problem, we explored the idea of using unsupervised clustering to construct a variety of auxiliary tasks from unlabeled data or existing labeled data. We found that some of these newly constructed tasks could exhibit semantic meanings corresponding to certain human-specific attributes, but some were non-ideal. In order to effectively reduce the impact of non-ideal auxiliary tasks on the main task, we further proposed a novel meta-learning-based multi-task learning approach, which trained the shared hidden layers on auxiliary tasks, while the meta-optimization objective was to minimize the loss on the main task, ensuring that the optimizing direction led to an improvement on the main task. Experimental results across five image datasets demonstrated that the proposed method significantly outperformed existing single task learning, semi-supervised learning, and some data augmentation methods, including an improvement of more than 9% on the Omniglot dataset.

scholarly journals Towards Understanding Clustering Problems and Algorithms: An Instance Space Analysis

Algorithms ◽  
2021 ◽  
Vol 14 (3) ◽  
pp. 95
Author(s):  
Luiz Henrique dos Santos Fernandes ◽  
Ana Carolina Lorena ◽  
Kate Smith-Miles
Keyword(s):  
Clustering Algorithms ◽  
Space Analysis ◽  
Meta Learning ◽  
Instance Space ◽  
Meta Analyses ◽  
The Impact ◽  
First Time ◽  
The Relationship ◽  
Clustering Problems ◽  
Selection Of

Various criteria and algorithms can be used for clustering, leading to very distinct outcomes and potential biases towards datasets with certain structures. More generally, the selection of the most effective algorithm to be applied for a given dataset, based on its characteristics, is a problem that has been largely studied in the field of meta-learning. Recent advances in the form of a new methodology known as Instance Space Analysis provide an opportunity to extend such meta-analyses to gain greater visual insights of the relationship between datasets’ characteristics and the performance of different algorithms. The aim of this study is to perform an Instance Space Analysis for the first time for clustering problems and algorithms. As a result, we are able to analyze the impact of the choice of the test instances employed, and the strengths and weaknesses of some popular clustering algorithms, for datasets with different structures.

scholarly journals Short Note on Comparing Stacking Modelling Versus Cannistraci-Hebb Adaptive Network Automata for Link Prediction in Complex Networks

2021 ◽  
Author(s):  
Alessandro Muscoloni ◽  
Carlo Vittorio Cannistraci
Keyword(s):  
Complex Networks ◽  
Link Prediction ◽  
Short Note ◽  
Machine Intelligence ◽  
Learning Method ◽  
Brute Force ◽  
Meta Learning ◽  
Squeeze Out ◽  
The Impact ◽  
Better Than

Link prediction is an iconic problem in complex networks because deals with the ability to predict nonobserved existing or future parts of the network structure. The impact of this prediction on real applications can be disruptive: from prediction of covert links between terrorists in their social networks to repositioning of drugs in molecular diseasome networks. Here we compare: (1) an ensemble meta-learning method (Ghasemian et al.), which uses an artificial intelligence (AI) stacking strategy to create a single meta-model from hundreds of other models; (2) a structural predictability method (SPM, Lü et al.), which relies on a theory derived from quantum mechanics and does not assume any model; (3) a modelling rule named Cannistraci-Hebb (CH, Muscoloni et al.), which relies on one brain-bioinspired model adapting to the intrinsic network structure.We conclude that brute-force stacking of algorithms by AI does not perform better than (and is often significantly outperformed by) SPM and one simple brain-bioinspired rule such as CH. This agrees with the Gödel incompleteness: stacking is optimal but incomplete, you cannot squeeze out more than what is already in your features. Hence, we should also pursue AI that resembles human-like physical ‘understanding’ of simple generalized rules associated to complexity. The future might be populated by AI that ‘steals for us the fire from Gods’, towards machine intelligence that creates new rules rather than stacking the ones already known.

scholarly journals Few-Shot Classification of Aerial Scene Images via Meta-Learning

2020 ◽  
Vol 13 (1) ◽  
pp. 108
Author(s):  
Pei Zhang ◽  
Yunpeng Bai ◽  
Dong Wang ◽  
Bendu Bai ◽  
Ying Li
Keyword(s):  
Classification Problem ◽  
Training Data ◽  
Scene Classification ◽  
Shot Classification ◽  
Training Stage ◽  
Testing Stage ◽  
Meta Learning ◽  
Cosine Distance ◽  
The Impact

Convolutional neural network (CNN) based methods have dominated the field of aerial scene classification for the past few years. While achieving remarkable success, CNN-based methods suffer from excessive parameters and notoriously rely on large amounts of training data. In this work, we introduce few-shot learning to the aerial scene classification problem. Few-shot learning aims to learn a model on base-set that can quickly adapt to unseen categories in novel-set, using only a few labeled samples. To this end, we proposed a meta-learning method for few-shot classification of aerial scene images. First, we train a feature extractor on all base categories to learn a representation of inputs. Then in the meta-training stage, the classifier is optimized in the metric space by cosine distance with a learnable scale parameter. At last, in the meta-testing stage, the query sample in the unseen category is predicted by the adapted classifier given a few support samples. We conduct extensive experiments on two challenging datasets: NWPU-RESISC45 and RSD46-WHU. The experimental results show that our method yields state-of-the-art performance. Furthermore, several ablation experiments are conducted to investigate the effects of dataset scale, the impact of different metrics and the number of support shots; the experiment results confirm that our model is specifically effective in few-shot settings.

Formation of Lunar Craters and Bright Rays as a Result of Meteorite Impacts

1962 ◽  
Vol 14 ◽  
pp. 415-418
Author(s):  
K. P. Stanyukovich ◽  
V. A. Bronshten
Keyword(s):  
Explosive Charge ◽  
The Moon ◽  
Meteorite Impacts ◽  
The Earth ◽  
Lunar Craters ◽  
The Impact

The phenomena accompanying the impact of large meteorites on the surface of the Moon or of the Earth can be examined on the basis of the theory of explosive phenomena if we assume that, instead of an exploding meteorite moving inside the rock, we have an explosive charge (equivalent in energy), situated at a certain distance under the surface.

The Geosciences Applied to Lunar Exploration

1962 ◽  
Vol 14 ◽  
pp. 169-257 ◽  
Author(s):  
J. Green
Keyword(s):  
Lunar Surface ◽  
Probable Mechanism ◽  
Point Of View ◽  
Lunar Exploration ◽  
Geological Model ◽  
Apply Geophysics ◽  
Surface Features ◽  
The Impact

The term geo-sciences has been used here to include the disciplines geology, geophysics and geochemistry. However, in order to apply geophysics and geochemistry effectively one must begin with a geological model. Therefore, the science of geology should be used as the basis for lunar exploration. From an astronomical point of view, a lunar terrain heavily impacted with meteors appears the more reasonable; although from a geological standpoint, volcanism seems the more probable mechanism. A surface liberally marked with volcanic features has been advocated by such geologists as Bülow, Dana, Suess, von Wolff, Shaler, Spurr, and Kuno. In this paper, both the impact and volcanic hypotheses are considered in the application of the geo-sciences to manned lunar exploration. However, more emphasis is placed on the volcanic, or more correctly the defluidization, hypothesis to account for lunar surface features.

Asteroid and Comet Impact Speeds upon Mars: Significance for Panspermia and the Supply of Organics

1997 ◽  
Vol 161 ◽  
pp. 197-201 ◽  
Author(s):  
Duncan Steel
Keyword(s):  
Probability Distributions ◽  
Regions Of Interest ◽  
Significant Fraction ◽  
Organic Chemicals ◽  
Impact Speed ◽  
The Mean ◽  
The Impact

AbstractWhilst lithopanspermia depends upon massive impacts occurring at a speed above some limit, the intact delivery of organic chemicals or other volatiles to a planet requires the impact speed to be below some other limit such that a significant fraction of that material escapes destruction. Thus the two opposite ends of the impact speed distributions are the regions of interest in the bioastronomical context, whereas much modelling work on impacts delivers, or makes use of, only the mean speed. Here the probability distributions of impact speeds upon Mars are calculated for (i) the orbital distribution of known asteroids; and (ii) the expected distribution of near-parabolic cometary orbits. It is found that cometary impacts are far more likely to eject rocks from Mars (over 99 percent of the cometary impacts are at speeds above 20 km/sec, but at most 5 percent of the asteroidal impacts); paradoxically, the objects impacting at speeds low enough to make organic/volatile survival possible (the asteroids) are those which are depleted in such species.

Organic Syntheses During the Impact of a Comet with a Gaseous Planet

1997 ◽  
Vol 161 ◽  
pp. 189-195
Author(s):  
Cesare Guaita ◽  
Roberto Crippa ◽  
Federico Manzini
Keyword(s):  
Polymeric Material ◽  
Molecular Form ◽  
Parent Compound ◽  
Blue Filter ◽  
Organic Syntheses ◽  
The Impact

AbstractA large amount of CO has been detected above many SL9/Jupiter impacts. This gas was never detected before the collision. So, in our opinion, CO was released from a parent compound during the collision. We identify this compound as POM (polyoxymethylene), a formaldehyde (HCHO) polymer that, when suddenly heated, reformes monomeric HCHO. At temperatures higher than 1200°K HCHO cannot exist in molecular form and the most probable result of its decomposition is the formation of CO. At lower temperatures, HCHO can react with NH3 and/or HCN to form high UV-absorbing polymeric material. In our opinion, this kind of material has also to be taken in to account to explain the complex evolution of some SL9 impacts that we observed in CCD images taken with a blue filter.

Hydrogen Cyanide Polymers from the Impact of Comet P/Shoemaker-Levy 9 on Jupiter

1997 ◽  
Vol 161 ◽  
pp. 179-187
Author(s):  
Clifford N. Matthews ◽  
Rose A. Pesce-Rodriguez ◽  
Shirley A. Liebman
Keyword(s):  
Amino Acids ◽  
Solar System ◽  
Hydrogen Cyanide ◽  
Nitrogen Heterocycles ◽  
Laboratory Studies ◽  
Heterogeneous Solids ◽  
The Many ◽  
Comet Halley ◽  
The Impact ◽  
By Products

AbstractHydrogen cyanide polymers – heterogeneous solids ranging in color from yellow to orange to brown to black – may be among the organic macromolecules most readily formed within the Solar System. The non-volatile black crust of comet Halley, for example, as well as the extensive orangebrown streaks in the atmosphere of Jupiter, might consist largely of such polymers synthesized from HCN formed by photolysis of methane and ammonia, the color observed depending on the concentration of HCN involved. Laboratory studies of these ubiquitous compounds point to the presence of polyamidine structures synthesized directly from hydrogen cyanide. These would be converted by water to polypeptides which can be further hydrolyzed to α-amino acids. Black polymers and multimers with conjugated ladder structures derived from HCN could also be formed and might well be the source of the many nitrogen heterocycles, adenine included, observed after pyrolysis. The dark brown color arising from the impacts of comet P/Shoemaker-Levy 9 on Jupiter might therefore be mainly caused by the presence of HCN polymers, whether originally present, deposited by the impactor or synthesized directly from HCN. Spectroscopic detection of these predicted macromolecules and their hydrolytic and pyrolytic by-products would strengthen significantly the hypothesis that cyanide polymerization is a preferred pathway for prebiotic and extraterrestrial chemistry.

Sign in / Sign up

Export Citation Format

Share Document