Pedro F. da Costa
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Pedro F. da Costa has a total of 51 co-authors. Here are the top co-authors by number of shared publications:
- Robert Leech
King’s College London, London, United Kingdom
4 shared publications - Emily Jane Harrison Jones
Centre for Brain and Cognitive Development, Department of Psychological Sciences, Birkbeck, University of London
3 shared publications - Anna Gui
Centre for Brain and Cognitive Development, Birkbeck College, University of London, London, UK
2 shared publications - Danilo Bzdok
Mila - Quebec Artificial Intelligence Institute, Montreal, Canada
2 shared publications - Elena Veronika Throm
Department of Psychological Science Centre for Brain and Cognitive Development, Birkbeck, University of London London UK
2 shared publications - Jessica Dafflon
Data Science and Sharing Team, Functional Magnetic Resonance Imaging Facility, National Institute of Mental Health, Bethesda, USA
2 shared publications
Latest Publications
- Open Access
- 8 January 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Storage
- Vol. 21 (1) , 1-31
Holographic Storage for the Cloud: advances and challenges
Holographic Storage is an old idea that has always promised high density and fast random access, but has never been commercially competitive with Hard Disk Drives (HDDs) and Solid State Devices (SSDs). In Project HSD at Microsoft Research we asked the question: “Does holographic storage finally make sense for cloud storage?” This article describes our journey toward answering this question. We achieved 1.8× higher density than the previous state-of-the-art, using commodity components available today and leveraging machine learning to compensate for the noise and distortions introduced by commodity components. This uncovered two new challenges which are the focus of this article: achieving high end-to-end energy efficiency without sacrificing capacity, and spatial multiplexing without mechanical movement. Improving end-to-end energy efficiency requires joint optimization across low-level media parameters and higher-level system parameters that govern background maintenance operations such as read refresh and garbage collection. We developed new physics models of the media; analytic and simulation models of the media access and background media maintenance; and workload-driven optimization to find optimal parameter combinations. These techniques resulted in a 14× improvement over the previous approach for typical workloads without sacrificing capacity. We also designed the first scalable and mechanical movement free spatial multiplexing system for holographic storage. Despite these advances, we conclude that currently, holographic storage is still far from the combination of density, capacity scaling, and energy efficiency needed to compete with the incumbent technologies. We need fundamental advances in the physical media that improve energy efficiency by another 1–2 orders of magnitude without reducing data density. Further advances in optics are also required to achieve spatial multiplexing that is simultaneously scalable, low-loss, and high-density.
- 8 January 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Storage
- Vol. 21 (1) , 1-31
Open AccessHolographic Storage for the Cloud: advances and challenges
Holographic Storage is an old idea that has always promised high density and fast random access, but has never been commercially competitive with Hard Disk Drives (HDDs) and Solid State Devices (SSDs). In Project HSD at Microsoft Research we asked the question: “Does holographic storage finally make sense for cloud storage?” This article describes our journey toward answering this question. We achieved 1.8× higher density than the previous state-of-the-art, using commodity components available today and leveraging machine learning to compensate for the noise and distortions introduced by commodity components. This uncovered two new challenges which are the focus of this article: achieving high end-to-end energy efficiency without sacrificing capacity, and spatial multiplexing without mechanical movement. Improving end-to-end energy efficiency requires joint optimization across low-level media parameters and higher-level system parameters that govern background maintenance operations such as read refresh and garbage collection. We developed new physics models of the media; analytic and simulation models of the media access and background media maintenance; and workload-driven optimization to find optimal parameter combinations. These techniques resulted in a 14× improvement over the previous approach for typical workloads without sacrificing capacity. We also designed the first scalable and mechanical movement free spatial multiplexing system for holographic storage. Despite these advances, we conclude that currently, holographic storage is still far from the combination of density, capacity scaling, and energy efficiency needed to compete with the incumbent technologies. We need fundamental advances in the physical media that improve energy efficiency by another 1–2 orders of magnitude without reducing data density. Further advances in optics are also required to achieve spatial multiplexing that is simultaneously scalable, low-loss, and high-density.
- Open Access
- 26 November 2024
- Published by Wiley in Developmental Science
- Vol. 28 (1) , e13592
Combining Real‐Time Neuroimaging With Machine Learning to Study Attention to Familiar Faces During Infancy: A Proof of Principle Study
Looking at caregivers’ faces is important for early social development, and there is a concomitant increase in neural correlates of attention to familiar versus novel faces in the first 6 months. However, by 12 months of age brain responses may not differentiate between familiar and unfamiliar faces. Traditional group‐based analyses do not examine whether these ‘null’ findings stem from a true lack of preference within individual infants, or whether groups of infants show individually strong but heterogeneous preferences for familiar versus unfamiliar faces. In a preregistered proof‐of‐principle study, we applied Neuroadaptive Bayesian Optimisation (NBO) to test how individual infants’ neural responses vary across faces differing in familiarity. Sixty‐one 5–12‐month‐olds viewed faces resulting from gradually morphing a familiar (primary caregiver) into an unfamiliar face. Electroencephalography (EEG) data from fronto‐central channels were analysed in real‐time. After the presentation of each face, the Negative central (Nc) event‐related potential (ERP) amplitude was calculated. A Bayesian Optimisation algorithm iteratively selected the next stimulus until it identified the stimulus eliciting the strongest Nc for that infant. Attrition (15%) was lower than in traditional studies (22%). Although there was no group‐level Nc‐difference between familiar versus unfamiliar faces, an optimum was predicted in 85% of the children, indicating individual‐level attentional preferences. Traditional analyses based on infants’ predicted optimum confirmed NBO can identify subgroups based on brain activation. Optima were not related to age and social behaviour. NBO suggests the lack of overall familiar/unfamiliar‐face attentional preference in middle infancy is explained by heterogeneous preferences, rather than a lack of preference within individual infants.
- 26 November 2024
- Published by Wiley in Developmental Science
- Vol. 28 (1) , e13592
Open AccessCombining Real‐Time Neuroimaging With Machine Learning to Study Attention to Familiar Faces During Infancy: A Proof of Principle Study
Looking at caregivers’ faces is important for early social development, and there is a concomitant increase in neural correlates of attention to familiar versus novel faces in the first 6 months. However, by 12 months of age brain responses may not differentiate between familiar and unfamiliar faces. Traditional group‐based analyses do not examine whether these ‘null’ findings stem from a true lack of preference within individual infants, or whether groups of infants show individually strong but heterogeneous preferences for familiar versus unfamiliar faces. In a preregistered proof‐of‐principle study, we applied Neuroadaptive Bayesian Optimisation (NBO) to test how individual infants’ neural responses vary across faces differing in familiarity. Sixty‐one 5–12‐month‐olds viewed faces resulting from gradually morphing a familiar (primary caregiver) into an unfamiliar face. Electroencephalography (EEG) data from fronto‐central channels were analysed in real‐time. After the presentation of each face, the Negative central (Nc) event‐related potential (ERP) amplitude was calculated. A Bayesian Optimisation algorithm iteratively selected the next stimulus until it identified the stimulus eliciting the strongest Nc for that infant. Attrition (15%) was lower than in traditional studies (22%). Although there was no group‐level Nc‐difference between familiar versus unfamiliar faces, an optimum was predicted in 85% of the children, indicating individual‐level attentional preferences. Traditional analyses based on infants’ predicted optimum confirmed NBO can identify subgroups based on brain activation. Optima were not related to age and social behaviour. NBO suggests the lack of overall familiar/unfamiliar‐face attentional preference in middle infancy is explained by heterogeneous preferences, rather than a lack of preference within individual infants.
- Top Cited PapersOpen Access
- 29 June 2022
- Published by Springer Nature in Nature Communications
- Vol. 13 (1) , 1-13
A guided multiverse study of neuroimaging analyses
For most neuroimaging questions the range of possible analytic choices makes it unclear how to evaluate conclusions from any single analytic method. One possible way to address this issue is to evaluate all possible analyses using a multiverse approach, however, this can be computationally challenging and sequential analyses on the same data can compromise predictive power. Here, we establish how active learning on a low-dimensional space capturing the inter-relationships between pipelines can efficiently approximate the full spectrum of analyses. This approach balances the benefits of a multiverse analysis without incurring the cost on computational and predictive power. We illustrate this approach with two functional MRI datasets (predicting brain age and autism diagnosis) demonstrating how a multiverse of analyses can be efficiently navigated and mapped out using active learning. Furthermore, our presented approach not only identifies the subset of analysis techniques that are best able to predict age or classify individuals with autism spectrum disorder and healthy controls, but it also allows the relationships between analyses to be quantified.
- 29 June 2022
- Published by Springer Nature in Nature Communications
- Vol. 13 (1) , 1-13
Top Cited PapersOpen AccessA guided multiverse study of neuroimaging analyses
For most neuroimaging questions the range of possible analytic choices makes it unclear how to evaluate conclusions from any single analytic method. One possible way to address this issue is to evaluate all possible analyses using a multiverse approach, however, this can be computationally challenging and sequential analyses on the same data can compromise predictive power. Here, we establish how active learning on a low-dimensional space capturing the inter-relationships between pipelines can efficiently approximate the full spectrum of analyses. This approach balances the benefits of a multiverse analysis without incurring the cost on computational and predictive power. We illustrate this approach with two functional MRI datasets (predicting brain age and autism diagnosis) demonstrating how a multiverse of analyses can be efficiently navigated and mapped out using active learning. Furthermore, our presented approach not only identifies the subset of analysis techniques that are best able to predict age or classify individuals with autism spectrum disorder and healthy controls, but it also allows the relationships between analyses to be quantified.
- 3 May 2022
- Published by Wiley in Infant and Child Development
- Vol. 31 (5)
Proving and improving the reliability of infant research with neuroadaptive Bayesian optimization
The field of infant research is not immune from the reproducibility crisis in cognitive science and psychology. In their recent methodological article, Byers‐Heinlein et al. (2021) invited infant researchers to commit to produce robust findings by reporting reliability metrics for their variables of interest, improving data quality and quantity, and moving towards more sophisticated paradigms and analyses. We present a novel artificial intelligence‐enriched individualized approach that, in our view, is particularly promising to shed new light on infant and child development and promote good research practice in the field; neuroadaptive Bayesian optimization (NBO). NBO is a transformative method where the collected brain or behavioural data are processed in real time and used to identify the stimuli that maximize the individual's response. Applying NBO to infant research goes in the direction proposed by Byers‐Heinlein et al. (2021) and further, the method requires careful a priori choices that effectively correspond to preregistering the experimental design and analytic pipeline. In this commentary, we examine how the NBO approach embeds the six proposed solutions for more reliable infant research, encouraging transparency of the planned analyses and robustness of findings.
- 3 May 2022
- Published by Wiley in Infant and Child Development
- Vol. 31 (5)
Proving and improving the reliability of infant research with neuroadaptive Bayesian optimization
The field of infant research is not immune from the reproducibility crisis in cognitive science and psychology. In their recent methodological article, Byers‐Heinlein et al. (2021) invited infant researchers to commit to produce robust findings by reporting reliability metrics for their variables of interest, improving data quality and quantity, and moving towards more sophisticated paradigms and analyses. We present a novel artificial intelligence‐enriched individualized approach that, in our view, is particularly promising to shed new light on infant and child development and promote good research practice in the field; neuroadaptive Bayesian optimization (NBO). NBO is a transformative method where the collected brain or behavioural data are processed in real time and used to identify the stimuli that maximize the individual's response. Applying NBO to infant research goes in the direction proposed by Byers‐Heinlein et al. (2021) and further, the method requires careful a priori choices that effectively correspond to preregistering the experimental design and analytic pipeline. In this commentary, we examine how the NBO approach embeds the six proposed solutions for more reliable infant research, encouraging transparency of the planned analyses and robustness of findings.
- Open Access
Neuroimaging: into the Multiverse
A bstract: For most neuroimaging questions the huge range of possible analytic choices leads to the possibility that conclusions from any single analytic approach may be misleading. Examples of possible choices include the motion regression approach used and smoothing and threshold factors applied during the processing pipeline. Although it is possible to perform a multiverse analysis that evaluates all possible analytic choices, this can be computationally challenging and repeated sequential analyses on the same data can compromise inferential and predictive power. Here, we establish how active learning on a low-dimensional space that captures the inter-relationships between analysis approaches can be used to efficiently approximate the whole multiverse of analyses. This approach balances the benefits of a multiverse analysis without the accompanying cost to statistical power, computational power and the integrity of inferences. We illustrate this approach with a functional MRI dataset of functional connectivity across adolescence, demonstrating how a multiverse of graph theoretic and simple pre-processing steps can be efficiently navigated using active learning. Our study shows how this approach can identify the subset of analysis techniques (i.e., pipelines) which are best able to predict participants’ ages, as well as allowing the performance of different approaches to be quantified.
Open AccessNeuroimaging: into the Multiverse
A bstract: For most neuroimaging questions the huge range of possible analytic choices leads to the possibility that conclusions from any single analytic approach may be misleading. Examples of possible choices include the motion regression approach used and smoothing and threshold factors applied during the processing pipeline. Although it is possible to perform a multiverse analysis that evaluates all possible analytic choices, this can be computationally challenging and repeated sequential analyses on the same data can compromise inferential and predictive power. Here, we establish how active learning on a low-dimensional space that captures the inter-relationships between analysis approaches can be used to efficiently approximate the whole multiverse of analyses. This approach balances the benefits of a multiverse analysis without the accompanying cost to statistical power, computational power and the integrity of inferences. We illustrate this approach with a functional MRI dataset of functional connectivity across adolescence, demonstrating how a multiverse of graph theoretic and simple pre-processing steps can be efficiently navigated using active learning. Our study shows how this approach can identify the subset of analysis techniques (i.e., pipelines) which are best able to predict participants’ ages, as well as allowing the performance of different approaches to be quantified.
- Open Access
Normative modelling using deep autoencoders: a multi-cohort study on mild cognitive impairment and Alzheimer’s disease
Normative modelling is an emerging method for quantifying how individuals deviate from the healthy populational pattern. Several machine learning models have been implemented to develop normative models to investigate brain disorders, including regression, support vector machines and Gaussian process models. With the advance of deep learning technology, the use of deep neural networks has also been proposed. In this study, we assessed normative models based on deep autoencoders using structural neuroimaging data from patients with Alzheimer’s disease (n=206) and mild cognitive impairment (n=354). We first trained the autoencoder on an independent dataset (UK Biobank dataset) with 11,034 healthy controls. Then, we estimated how each patient deviated from this norm and established which brain regions were associated to this deviation. Finally, we compared the performance of our normative model against traditional classifiers. As expected, we found that patients exhibited deviations according to the severity of their clinical condition. The model identified medial temporal regions, including the hippocampus, and the ventricular system as critical regions for the calculation of the deviation score. Overall, the normative model had comparable cross-cohort generalizability to traditional classifiers. In order to promote open science, we are making all scripts and the trained models available to the wider research community.
Open AccessNormative modelling using deep autoencoders: a multi-cohort study on mild cognitive impairment and Alzheimer’s disease
Normative modelling is an emerging method for quantifying how individuals deviate from the healthy populational pattern. Several machine learning models have been implemented to develop normative models to investigate brain disorders, including regression, support vector machines and Gaussian process models. With the advance of deep learning technology, the use of deep neural networks has also been proposed. In this study, we assessed normative models based on deep autoencoders using structural neuroimaging data from patients with Alzheimer’s disease (n=206) and mild cognitive impairment (n=354). We first trained the autoencoder on an independent dataset (UK Biobank dataset) with 11,034 healthy controls. Then, we estimated how each patient deviated from this norm and established which brain regions were associated to this deviation. Finally, we compared the performance of our normative model against traditional classifiers. As expected, we found that patients exhibited deviations according to the severity of their clinical condition. The model identified medial temporal regions, including the hippocampus, and the ventricular system as critical regions for the calculation of the deviation score. Overall, the normative model had comparable cross-cohort generalizability to traditional classifiers. In order to promote open science, we are making all scripts and the trained models available to the wider research community.