ライフサイエンスコーパス: learn

1 visuospatial discriminations (reward-guided learning).

2 ty of interpreting the complex features they learn.

3 ly dissociable from the awareness of what is learned.

4 nterpretation of what the neural network has learned.

5 al inference dictate that uncertainty shapes learning.

6 ontrol false discoveries for class-imbalance learning.

7 tably retained even more than 200 days after learning.

8 or file handling, visualization, and machine learning.

9 on to image classification and reinforcement learning.

10 s >2000 behavioral features based on machine learning.

11 ely untested method of delivering simulation learning.

12 her, when and how to try is central to human learning.

13 ategies in favor of low-level implicit motor learning.

14 s variability but variability can facilitate learning.

15 tegrated predictions that may improve future learning.

16 n the projection neurons mediates appetitive learning.

17 d joint effects of these factors upon reward learning.

18 ikely contribute to independent processes of learning.

19 plays a key role in motor control and motor learning.

20 ich limits our chances to improve intergroup learning.

21 enhancement, which has value for educational learning.

22 MARS uses deep learning to learn a cell embedding function as well as a set of land

23 the past 85 years of antibiotic use, we have learned a great deal about how these 'miracle' drugs wor

24 A crucial aspect when learning a language is discovering the rules that govern

25 category emerges in the OT within minutes of learning a novel odor-reward association, whereas the pP

26 solutions by using them to interact with and learn about the environment.

27 How do we learn about what to learn about?

28 ich participants were assumed to attend (and learn about) only one of several cues on each trial.

29 How do we learn about what to learn about?

30 present in infancy and aid understanding and learning about the social environment.

31 tion (TMLE) paired with the ensemble machine learning algorithm Super Learner, and compared these wit

32 eveloped a new systems-biology-informed deep learning algorithm that incorporates the system of ordin

33 dvances in earthquake monitoring with a deep-learning algorithm to image a fault zone hosting a 4-yea

34 A deep learning algorithm was used to segment all baseline OCT

35 ction from first principles for each machine-learning algorithm, we observe that there is typically a

36 In this study, by using machine learning algorithms and the functional connections of th

37 As deep learning algorithms drive the progress in protein struct

38 everal hierarchical extensions of well-known learning algorithms have been proposed.

39 t significantly outperformed shallow machine-learning algorithms in benchmark comparisons, showing ne

40 with HLA-binding properties by using machine-learning algorithms may increase the prediction accuracy

41 ne interactions for the construction of deep-learning algorithms that benefit from expert knowledge a

42 training and a testing set and used machine-learning algorithms to classify participants based on ps

43 work is to evaluate the efficacy of machine learning algorithms to cluster the patients into discrim

44 Machine learning algorithms were developed to identify a combina

45 t decisions were modeled using reinforcement learning algorithms.

46 his was more evident for some of the machine learning algorithms.

47 Reinforcement learning allows organisms to predict future outcomes and

48 tics, in vivo electrophysiology, and machine learning analysis, we find that a subset of neurons in t

49 he rich and complex components that comprise learning and decision-making.

50 use of nonlinear kernel methods for machine learning and dimension reduction of high-dimensional dat

51 nvestigate more abstract, higher-order human learning and knowledge generalization.

52 mpal neurogenesis plays an important role in learning and memory function throughout life.

53 Whereas DG's function in spatial learning and memory has been extensively investigated, i

54 itical role in many processes fundamental to learning and memory in health and are implicated in Alzh

55 tes feeding-relevant biological signals with learning and memory processes to regulate feeding.

56 conditioning to facilitate associative fear learning and memory.

57 ritical for neurological function, including learning and memory.

58 Physical exercise is a powerful modulator of learning and memory.

59 lays a causal role in the acquisition of new learning and not just in the extinction or reversal of p

60 Statistical learning and probabilistic prediction are fundamental pr

61 studied at this merging superhighway of deep learning and protein structure prediction.

62 opment of force accuracy was associated with learning and reduced falls.

63 nd Attachment, Reward Responsiveness, Reward Learning and Reward Valuation constructs.

64 Here, we investigate how reinforcement learning and selective attention interact during learnin

65 and structural changes in key regions of the learning and sensory systems associated with anesthesia-

66 (B) agonist baclofen impaired motor sequence learning and visuomotor learning in 20 young healthy par

67 as the testing effect or as retrieval-based learning) and consider directions for future research.

68 rojecting neurons disrupted Pavlovian reward learning, and activation of these cells promoted the acq

69 educational manipulation to improve memory, learning, and transfer of theory-rich content.

70 sing multiscale mechanistic docking, machine learning, and X-ray crystallography, pointing the way fo

71 Here, we developed a machine-learning approach to identify small molecules that broad

72 ovarian tumour cohort and develop a machine learning approach to molecularly classify and characteri

73 Here, we introduce a bespoke machine-learning approach, hierarchical statistical mechanical m

74 Using a machine learning approach, we built gene expression-based models

75 We apply machine learning approaches to a comprehensive vascular plant da

76 ries, including network analysis and machine learning, are well placed for analysing these data but m

77 ical projection neurons, validating transfer learning as a tool to adapt the model to novel categorie

78 xtinction or reversal of previously acquired learning, as previously thought.

79 ories (A items) during overlapping pair (BC) learning, as well as learning-related representational c

80 as the application of multitask and transfer learning, as well as the use of biologically motivated,

81 peline using Statistical testing and Machine Learning (ASAP-SML), to identify features that distingui

82 EMG showed that learning augments the muscular response evoked by motone

83 her with a "logical" statistical and machine learning-based approach, identified a number of molecula

84 uence data, we developed MapPred, a new deep learning-based contact prediction method.

85 A specific class of deep learning-based methods allows for the prediction of regu

86 acked is a major bottleneck in standard deep learning-based models.

87 sponse, we employed high-performance machine learning-based NER tools for concept recognition and tra

88 We propose DeepCleave, the first deep learning-based predictor of protease-specific substrates

89 Practical workshops were useful for learning basic concepts about ultrasound imaging, allowi

90 hibited selectivity for stimulus rank during learning, but not before or after.

91 ed clustering method to extract the patterns learned by the ResNet models.

92 ing circuits may be influenced early in song learning by a cortical region (NIf) at the interface bet

93 ing may also underlie its contribution to MB learning by representing relational structure in a cogni

94 In this Review, we discuss how machine learning can aid early diagnosis and interpretation of m

95 , radiomics features extraction, and machine learning can be used in a pipeline to automatically dete

96 Thus, deep learning can reveal the regulatory syntax predictive of

97 traction and, integrated with CNN-based deep learning, can boost the predictive accuracy.

98 Although social learning capabilities are taxonomically widespread, demo

99 On the basis of machine learning, CEFCIG reveals unique histone codes for transc

100 Finally, machine learning classification algorithms applied to group lass

101 or quantitatively with the Gene Oracle deep learning classifier.

102 at abstraction varies at different levels of learning, cognitive development, or cognitive ability.

103 The IED task measures visual discrimination learning, cognitive flexibility and specifically attenti

104 re of themodel used is set purely by machine learning considerations with little consideration of rep

105 Deep learning-corrected PET (PET(DL)) images were quantitativ

106 tional lecturing with evidence-based, active-learning course designs across the STEM disciplines and

107 odel was used to identify the periods of the learning curve.

108 tilation scans from free-breathing MRI (deep learning [DL] ventilation MRI)-derived specific ventilat

109 n forecast the occurrence of a global gap or learn effective individualized intervention policies.

110 Learning experience weakens the gap junctions and induce

111 e behavioral and neural data from a task-set learning experiment using a network model.

112 The learned factors reflect tissues with known biological si

113 evidence indicating that sex differences in learned fear inhibition are associated with altered mPFC

114 icks and problems when using them in machine learning for excited states of molecules.

115 ter than the models trained with single-task learning for predicting patients' individual symptom tra

116 other Python packages (e.g., Nilearn, Scikit-learn) for file handling, visualization, and machine lea

117 A popular deep learning framework (Keras) is applied to the problem of

118 The proposed deep learning framework is effective for such task.

119 We extend the classic transfer learning framework through ensemble and demonstrate its

120 Here we present an End-to-End deep learning framework, circDeep, to classify circular RNA f

121 Individuals differ in how they learn from experience.

122 icymakers, providers, and health centers can learn from high-achieving centers to promote early initi

123 grated for us to effectively engage with and learn from our world.

124 Here, we examine lessons learned from a variety of model systems, including yeast

125 esearch and COVID-19 and suggest how lessons learned from cancer research may impact SARS-CoV-2 resea

126 ult to grasp by visual analysis but could be learned from large-scale datasets.

127 tems manage light scattering and what can be learned from plants and animals to produce photonic mate

128 Lessons learned from this comparison were then harnessed for the

129 While learning from complications is useful, M&M does not meet

130 m observing outgroups.SIGNIFICANCE STATEMENT Learning from observing others is an efficient way to ac

131 enerates predictive or descriptive models by learning from training data rather than by being rigidly

132 ning and selective attention interact during learning from trial and error across age groups.

133 sing feature selection algorithm and machine learning, from which the accuracy of detection of positi

134 While deep learning has been applied to cell segmentation problems

135 als (whether wild or captive) rely on social learning has proved remarkably challenging.

136 Recently, deep learning has unlocked unprecedented success in various d

137 ral circuits underlying more direct forms of learning have been well established over the last centur

138 h-care system through the establishment of a learning health system built on digital data and innovat

139 One is model-free learning, i.e., simple reinforcement of rewarded actions

140 y systems associated with anesthesia-induced learning impairment.

141 There is much still to learn in the fluid biomarker field in FTD, but the creat

142 aired motor sequence learning and visuomotor learning in 20 young healthy participants of both sexes.

143 f neonatal anesthesia exposure on behavioral learning in adolescent subjects, and a variety of MRI te

144 humans exhibit two distinct strategies when learning in complex environments.

145 sion weighting of prediction errors benefits learning in health and is impaired in psychosis.

146 st, we asked if well-known features of motor learning in lab-based experiments generalize to a real-w

147 properties of CA1 interneurons 3 h following learning, in a form of oxidative eustress.

148 Machine learning is a branch of computer science and statistics

149 how that using prior knowledge to facilitate learning is accompanied by the evolution of a neural sch

150 This form of social learning is argued to reflect novel forms of social hier

151 However, it remains unclear whether learning is facilitated by non-rapid eye movement (NREM)

152 In real-world settings, learning is often characterised as intentional: learners

153 erated MR image reconstruction using machine learning is presented.

154 during the learning process, and the goal of learning is readily dissociable from the awareness of wh

155 e of success, and when success-biased social learning is unavailable.

156 key predictions that prestige-biased social learning is used when it constitutes an indirect cue of

157 (~20 Hz) at triplet transitions that indexes learning: it emerges with increased pattern repetitions;

158 mputational and neural account of why people learn less from observing outgroups.SIGNIFICANCE STATEME

159 Among other advances, deep-learning machine learning methods, including convolution

160 hat the contribution of hippocampus to place learning may also underlie its contribution to MB learni

161 uggests that a targeted modulation of reward learning may be a viable approach for novel intervention

162 work was used to elucidate the reinforcement-learning mechanisms that change in adolescence and into

163 the foundation to examine observational fear learning mechanisms that might contribute to fear and an

164 omputational modeling revealed that dominant learning mechanisms underpinning flexible behavior diffe

165 and fundamental changes in behaviors such as learning, memory, and social interactions.

166 MENT The dentate gyrus (DG) is important for learning, memory, pattern separation, and spatial naviga

167 on, time-memory for food sources, sleep, and learning/memory processes.

168 Here, we present a machine-learning method comparing projected typhoon tracks with

169 nsional (3D) U-Net and a coarse-to-fine deep learning method.

170 d biological interpretation across 8 machine learning methods and 4 different types of metagenomic da

171 Bayesian machine learning methods can be used for prospective prediction

172 nimal evidence that state-of-the-art machine learning methods can forecast the occurrence of a global

173 multivariate statistical models and machine learning methods for the classification of 6 types based

174 rediction enables the development of machine-learning methods to predict the likely biological activi

175 Among other advances, deep-learning machine learning methods, including convolutional neural network

176 ral Imaging (NIR-HSI), together with machine learning methods, is valuable to improve the efficiency

177 performance and outcomes of chemical machine learning methods.

178 th the scripts for training and testing deep learning methods.

179 CCS prediction using machine learning (ML) has recently shown promise in the field, b

180 Application of machine learning (ML) methods for the determination of the gas a

181 Machine learning (ML) provides powerful dimensionality reduction

182 The deep learning model allowed for fully automatic and robust se

183 rams per liter using a random forest machine-learning model based on 11 geospatial environmental para

184 shift calculation protocols using a machine learning model in conjunction with standard DFT methods.

185 The machine learning model pretrained on Fourier spectrum features a

186 We have trained a machine learning model to analyze the correlation between SARS-C

187 In conclusion, our machine learning model was able to identify EGFR-mutant patients

188 We propose a deep learning model, so-called CLPred, which uses a bidirecti

189 ues of choices, estimated by a reinforcement learning model, were regressed against BOLD signal.

190 The resulting machine learning models and segregation database are key to unlo

191 enetic and non-genetic factors, four machine learning models have close prediction results for the ph

192 Various deep learning models have gained success in image analysis in

193 e highlight specific achievements of machine learning models in the field of computational chemistry

194 s, BioConceptVec, via four different machine learning models on ~30 million PubMed abstracts.

195 nt participants and symptoms, our multi-task learning models perform statistically significantly bett

196 We used four machine learning models to produce flood susceptibility maps.

197 Reinforcement learning models treat the basal ganglia (BG) as an actor

198 Deep learning models were trained to use SD OCT retinal nerve

199 walkthrough for creating supervised machine learning models with current examples from the literatur

200 election can improve the accuracy of machine-learning models, but appropriate steps must be taken to

201 The training performance of all machine learning models, including six other algorithms, was eva

202 d the selected variables to multiple machine learning models.

203 Future research should focus on learning more about the use of existing tools rather tha

204 umption through its effects on reinforcement learning, motivation, and hedonic experience.

205 s of age by using the Mullen Scales of Early Learning (MSEL).

206 ter is devoted to the application of machine learning, namely, convolutional neural networks to solve

207 ion methods in this context, and apply it to learn network similarity and shared pathway activity for

208 Although applications of deep learning networks to real-world problems have become ubi

209 nerated activity that allows participants to learn new sensorimotor schemes.

210 caque monkeys received extensive training to learn novel visuospatial discriminations (reward-guided

211 provides evidence that human motor sequence learning occurs outside of M1.

212 tor Octbeta1R drives aversive and appetitive learning: Octbeta1R in the mushroom body alphabeta neuro

213 firmation bias may be adaptive for efficient learning of action-outcome contingencies, above and beyo

214 90-93% through the sparse regression machine learning of patterns.

215 d activity and thus tracked specifically the learning of reward predictive visual features.

216 Here, we conduct machine learning of serum metabolic patterns to detect early-sta

217 Statistical learning of transition patterns between sounds-a strikin

218 neurons to the training odorants to generate learned olfactory behavior.

219 e behavior in ASD was driven by less optimal learning on average within each age group.

220 Although there is still much to learn, our current understanding of tetrapyrrole biogene

221 tly, it is highly correlated with behavioral learning outcomes.

222 Both before and after learning, participants were also scanned while viewing i

223 Rather than impaired threat learning, pathological anxiety involves heightened skin

224 I characterize the typical learning performance in terms of the power spectrum of r

225 ressure values were calculated from the deep learning-predicted tonometer and mire diameters using th

226 gests that (1) natal magnetic inclination is learnt prior to fledging and (2) is used to provide lati

227 l: learners are aware of the goal during the learning process, and the goal of learning is readily di

228 uide each other's attention, prediction, and learning processes towards salient information, at the t

229 The machine learning produced highly accurate and robust classificat

230 We found that memory reactivation during learning promoted formation of differentiated representa

231 We found that contextual fear learning recruits a population of young ABNs that are re

232 Learning reduces variability but variability can facilit

233 ed in this respect, how the thalamus encodes learning-related information is still largely unknown.

234 g overlapping pair (BC) learning, as well as learning-related representational change for indirectly

235 ce of this outgroup deficit in observational learning remained unknown, which limits our chances to i

236 -quality case reports, and a specific set of learning resources.

237 where subjects solve multiple reinforcement learning (RL) problems differing in structural or sensor

238 oscientific implications: deep reinforcement learning (RL).

239 They could thus learn schemas of category locations by encoding specific

240 memory during training and acutely terminate learned search behavior in a subsequent recall test.

241 ar sensitization in the stress-enhanced fear learning (SEFL) model of PTSD, as well as associated cha

242 psychosis may emerge because of a failure to learn sensory statistics, resulting in an impaired repre

243 These findings imply that intergroup learning should rely on observing outcomes, rather than

244 ing a multifaceted role in socially adaptive learning.SIGNIFICANCE STATEMENT Adaptively navigating so

245 rsed to negative valence in a Pavlovian fear learning situation, where CeA ChR2 pairing increases def

246 Within-session learning slope may be a useful marker beyond performance

247 ation, and whether facilitation results from learning-specific processing.

248 When exposed to a subthreshold learning stimulus, juv ELE and juv-adol ELE formed lasti

249 Previous deep learning studies on optical coherence tomography (OCT) m

250 gical workflow recognition and report a deep learning system, that not only detects surgical phases,

251 to overcome is the amount of data needed by learning systems of this type.

252 the changes that occur in the brain as this learning takes place are poorly understood.

253 Here we developed a reversal learning task for head-fixed mice, monitored the activit

254 s performed a two-armed bandit reinforcement learning task.

255 peed in a two-stage sequential reinforcement-learning task.

256 rning tasks, i.e. model-free vs. model-based learning tasks, and their possible differential effects

257 We compared different motor-learning tasks, i.e. model-free vs. model-based learning

258 ecreased exponentially across trials in both learning tasks, optimal target selection (task 1) and op

259 ysiological plasticity and to distinct motor learning tasks, which suggests they represent separate c

260 n address the question of why humans seek to learn, teach, and innovate - three processes essential t

261 We tested several recent deep learning techniques including wide residual networks, dr

262 density functionals using supervised machine learning, termed NeuralXC.

263 We also learned that FMO3 is an essential modifier of the polyke

264 MBIL, NPC, and GES all learned that grade and lymph_nodes_positive are direct r

265 Neither GES nor NPC learned that HER2 and ER are direct risk factors.

266 the country, the authors reflect on lessons learned that may help leaders at other institutions miti

267 hypothesis is that training the algorithm to learn the morphological differences between patients wil

268 on to this problem would be for an animal to learn the values for spatially and temporally stable gra

269 of objects, than across blocks in which they learned the values of actions.

270 ty was higher across blocks in which animals learned the values of novel pairs of objects, than acros

271 Instead of learning the inverse mapping from a streaking trace to a

272 Hippocampal theta thus supports learning through two interleaved processes: strengthenin

273 tal studies suggest that animals can rapidly learn to identify odors and predict the rewards associat

274 mbine sparse mixture mapping with supervised learning to achieve bit error rates as low as 0.11% for

275 direct long-read RNA sequencing and machine learning to detect secondary structures in cellular RNAs

276 We applied machine learning to explain how specific interactions controlled

277 rovides encouragement for the use of machine learning to extract meaningful structural information fr

278 ion-seeking, attention, decision-making, and learning to help us survive in an uncertain world.

279 prioritize functional sites, we used machine learning to identify 59 features indicative of proteomic

280 MARS uses deep learning to learn a cell embedding function as well as a

281 ally innovative in that it also uses machine learning to perform cell tracking and lineage reconstruc

282 Here, we used EEG and machine learning to study how the brain processes auditory, visu

283 Finally, we use machine learning to test whether pairwise trophic interactions c

284 DeepH3, a deep residual neural network that learns to predict inter-residue distances and orientatio

285 Based on the lessons learned, to facilitate pipeline validation and catalyze

286 t application of the novel NMR-based machine learning tool "Small Molecule Accurate Recognition Techn

287 Our study probed baboons' capacity to learn two supra-regular grammars of different levels of

288 ty suggests a unified role for confidence in learning under different types of uncertainty across mam

289 findings from this and non-human studies on learning under perceptual uncertainty suggests a unified

290 Learning valence-based responses to favorable and unfavo

291 neurons increased during learning, with the learned values stably retained even more than 200 days a

292 We first demonstrate that learning via goal-directed behaviour indeed constrains m

293 of evidence indicates that visual perceptual learning (VPL) is enhanced by reward provided during tra

294 In contrast, reversal learning was impaired by D2R antagonism, but not D1R ant

295 tion, distributed leadership, and collective learning was used to facilitate adoption.

296 re we asked whether, in the context of motor learning where errors decrease across trials, people tak

297 om body alphabeta neurons processes aversive learning, whereas Octbeta1R in the projection neurons me

298 warded actions, and the other is model-based learning, which considers the structure of the environme

299 paminergic reward-prediction errors underlie learning, which renders stimuli 'wanted'.

300 y of these thalamic neurons increased during learning, with the learned values stably retained even m