Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
20,568
result(s) for
"Task Performance and Analysis"
Sort by:
Training cognition : optimizing efficiency, durability, and generalizability
\"This book describes research on training using cognitive psychology to build a complete empirical and theoretical picture of the training process. It includes a review of relevant cognitive psychological literature, a summary of recent laboratory experiments, a presentation of original theoretical ideas, and a discussion of possible applications to real-world training settings\"--Provided by publisher.
Book
Mastering diverse control tasks through world models
Developing a general algorithm that learns to solve tasks across a wide range of applications has been a fundamental challenge in artificial intelligence. Although current reinforcement-learning algorithms can be readily applied to tasks similar to what they have been developed for, configuring them for new application domains requires substantial human expertise and experimentation
1
,
2
. Here we present the third generation of Dreamer, a general algorithm that outperforms specialized methods across over 150 diverse tasks, with a single configuration. Dreamer learns a model of the environment and improves its behaviour by imagining future scenarios. Robustness techniques based on normalization, balancing and transformations enable stable learning across domains. Applied out of the box, Dreamer is, to our knowledge, the first algorithm to collect diamonds in
Minecraft
from scratch without human data or curricula. This achievement has been posed as a substantial challenge in artificial intelligence that requires exploring farsighted strategies from pixels and sparse rewards in an open world
3
. Our work allows solving challenging control problems without extensive experimentation, making reinforcement learning broadly applicable.
A general reinforcement-learning algorithm, called Dreamer, outperforms specialized expert algorithms across diverse tasks by learning a model of the environment and improving its behaviour by imagining future scenarios.
Journal Article
Task-free MRI predicts individual differences in brain activity during task performance
When asked to perform the same task, different individuals exhibit markedly different patterns of brain activity. This variability is often attributed to volatile factors, such as task strategy or compliance. We propose that individual differences in brain responses are, to a large degree, inherent to the brain and can be predicted from task-independent measurements collected at rest. Using a large set of task conditions, spanning several behavioral domains, we train a simple model that relates task-independent measurements to task activity and evaluate the model by predicting task activation maps for unseen subjects using magnetic resonance imaging. Our model can accurately predict individual differences in brain activity and highlights a coupling between brain connectivity and function that can be captured at the level of individual subjects.
Journal Article
Distributed coding of choice, action and engagement across the mouse brain
Vision, choice, action and behavioural engagement arise from neuronal activity that may be distributed across brain regions. Here we delineate the spatial distribution of neurons underlying these processes. We used Neuropixels probes
1
,
2
to record from approximately 30,000 neurons in 42 brain regions of mice performing a visual discrimination task
3
. Neurons in nearly all regions responded non-specifically when the mouse initiated an action. By contrast, neurons encoding visual stimuli and upcoming choices occupied restricted regions in the neocortex, basal ganglia and midbrain. Choice signals were rare and emerged with indistinguishable timing across regions. Midbrain neurons were activated before contralateral choices and were suppressed before ipsilateral choices, whereas forebrain neurons could prefer either side. Brain-wide pre-stimulus activity predicted engagement in individual trials and in the overall task, with enhanced subcortical but suppressed neocortical activity during engagement. These results reveal organizing principles for the distribution of neurons encoding behaviourally relevant variables across the mouse brain.
Recordings from 30,000 neurons in 42 brain regions are used to delineate the spatial distribution of neuronal activity underlying vision, choice, action and behavioural engagement in mice.
Journal Article
Training Cognition
Training is both a teaching and a learning experience, and just about everyone has had that experience. Training involves acquiring knowledge and skills. This newly acquired training information is meant to be applicable to specific activities, tasks, and jobs. In modern times, where jobs are increasingly more complex, training workers to perform successfully is of more importance than ever. The range of contexts in which training is required includes industrial, corporate, military, artistic, and sporting, at all levels from assembly line to executive function. The required training can take place in a variety of ways and settings, including the classroom, the laboratory, the studio, the playing field, and the work environment itself.
The general goal of this book is to describe the current state of research on training using cognitive psychology to build a complete empirical and theoretical picture of the training process. The book focuses on training cognition, as opposed to physical or fitness training. It attempts to show how to optimize training efficiency, durability, and generalizability. The book includes a review of relevant cognitive psychological literature, a summary of recent laboratory experiments, a presentation of original theoretical ideas, and a discussion of possible applications to real-world training settings.
eBook
Stopwords in technical language processing
There are increasing applications of natural language processing techniques for information retrieval, indexing, topic modelling and text classification in engineering contexts. A standard component of such tasks is the removal of stopwords, which are uninformative components of the data. While researchers use readily available stopwords lists that are derived from non-technical resources, the technical jargon of engineering fields contains their own highly frequent and uninformative words and there exists no standard stopwords list for technical language processing applications. Here we address this gap by rigorously identifying generic, insignificant, uninformative stopwords in engineering texts beyond the stopwords in general texts, based on the synthesis of alternative statistical measures such as term frequency, inverse document frequency, and entropy, and curating a stopwords dataset ready for technical language processing applications.
Journal Article
Effects of motor–cognitive training on dual-task performance in people with Parkinson’s disease: a systematic review and meta-analysis
Motor–cognitive training in Parkinson’s disease (PD) can positively affect gait and balance, but whether motor–cognitive (dual-task) performance improves is unknown. This meta-analysis, therefore, aimed to establish the current evidence on the effects of motor–cognitive training on dual-task performance in PD. Systematic searches were conducted in five databases and 11 studies with a total of 597 people (mean age: 68.9 years; mean PD duration: 6.8 years) were included. We found a mean difference in dual-task gait speed (0.12 m/s (95% CI 0.08, 0.17)), dual-task cadence (2.91 steps/min (95% CI 0.08, 5.73)), dual-task stride length (10.12 cm (95% CI 4.86, 15.38)) and dual-task cost on gait speed (− 8.75% (95% CI − 14.57, − 2.92)) in favor of motor–cognitive training compared to controls. The GRADE analysis revealed that the findings were based on high certainty evidence. Thus, we can for the first time systematically show that people with PD can improve their dual-task ability through motor–cognitive training.
Journal Article
Neural heterogeneity promotes robust learning
The brain is a hugely diverse, heterogeneous structure. Whether or not heterogeneity at the neural level plays a functional role remains unclear, and has been relatively little explored in models which are often highly homogeneous. We compared the performance of spiking neural networks trained to carry out tasks of real-world difficulty, with varying degrees of heterogeneity, and found that heterogeneity substantially improved task performance. Learning with heterogeneity was more stable and robust, particularly for tasks with a rich temporal structure. In addition, the distribution of neuronal parameters in the trained networks is similar to those observed experimentally. We suggest that the heterogeneity observed in the brain may be more than just the byproduct of noisy processes, but rather may serve an active and important role in allowing animals to learn in changing environments.
The authors show that heterogeneity in spiking neural networks improves accuracy and robustness of prediction for complex information processing tasks, results in optimal parameter distribution similar to experimental data and is metabolically efficient for learning tasks at varying timescales.
Journal Article
An evaluation of mental workload with frontal EEG
Using a wireless single channel EEG device, we investigated the feasibility of using short-term frontal EEG as a means to evaluate the dynamic changes of mental workload. Frontal EEG signals were recorded from twenty healthy subjects performing four cognitive and motor tasks, including arithmetic operation, finger tapping, mental rotation and lexical decision task. Our findings revealed that theta activity is the common EEG feature that increases with difficulty across four tasks. Meanwhile, with a short-time analysis window, the level of mental workload could be classified from EEG features with 65%-75% accuracy across subjects using a SVM model. These findings suggest that frontal EEG could be used for evaluating the dynamic changes of mental workload.
Journal Article
Explainable AI improves task performance in human–AI collaboration
Artificial intelligence (AI) provides considerable opportunities to assist human work. However, one crucial challenge of human–AI collaboration is that many AI algorithms operate in a black-box manner where the way how the AI makes predictions remains opaque. This makes it difficult for humans to validate a prediction made by AI against their own domain knowledge. For this reason, we hypothesize that augmenting humans with explainable AI improves task performance in human–AI collaboration. To test this hypothesis, we implement explainable AI in the form of visual heatmaps in inspection tasks conducted by domain experts. Visual heatmaps have the advantage that they are easy to understand and help to localize relevant parts of an image. We then compare participants that were either supported by (a) black-box AI or (b) explainable AI, where the latter supports them to follow AI predictions when the AI is accurate or overrule the AI when the AI predictions are wrong. We conducted two preregistered experiments with representative, real-world visual inspection tasks from manufacturing and medicine. The first experiment was conducted with factory workers from an electronics factory, who performed
assessments of whether electronic products have defects. The second experiment was conducted with radiologists, who performed
assessments of chest X-ray images to identify lung lesions. The results of our experiments with domain experts performing real-world tasks show that task performance improves when participants are supported by explainable AI with heatmaps instead of black-box AI. We find that explainable AI as a decision aid improved the task performance by 7.7 percentage points (95% confidence interval [CI]: 3.3% to 12.0%,
) in the manufacturing experiment and by 4.7 percentage points (95% CI: 1.1% to 8.3%,
) in the medical experiment compared to black-box AI. These gains represent a significant improvement in task performance.
Journal Article