ArticlePloS one2018
full-FORCE: A target-based method for training recurrent networks.
Article in PloS one, 2018. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 47 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
47 citing papers in PubMed.
- Inferring brain-wide interactions using data-constrained recurrent neural network models.Neuron · 2026Article
- Theory of temporal pattern learning in echo state networks.PNAS nexus · 2026Article
- Constructing biologically constrained RNNs via Dale's backpropagation and topologically informed pruning.Science advances · 2025Article
- Relative phase of membrane potential theta oscillations between individual hippocampal neurons code space.bioRxiv : the preprint server for biology · 2025Article
- Taming the chaos gently: a predictive alignment learning rule in recurrent neural networks.Nature communications · 2025Article
- Stable recurrent dynamics in heterogeneous neuromorphic computing systems using excitatory and inhibitory plasticity.Nature communications · 2025Article
- Comparison of FORCE trained spiking and rate neural networks shows spiking networks learn slowly with noisy, cross-trial firing rates.PLoS computational biology · 2025Article
- CONSTRUCTING BIOLOGICALLY CONSTRAINED RNNS VIA DALE'S BACKPROP AND TOPOLOGICALLY-INFORMED PRUNING.bioRxiv : the preprint server for biology · 2025Article
- Learning to express reward prediction error-like dopaminergic activity requires plastic representations of time.Nature communications · 2024Article
- Probing latent brain dynamics in Alzheimer's disease via recurrent neural network.Cognitive neurodynamics · 2024Article
- The impact of spike timing precision and spike emission reliability on decoding accuracy.Scientific reports · 2024Article
- Memorable first impressions.eLife · 2024Article
- Robust compression and detection of epileptiform patterns in ECoG using a real-time spiking neural network hardware framework.Nature communications · 2024Article
- Brain-inspired modular echo state network for EEG-based emotion recognition.Frontiers in neuroscience · 2024Article
- Exploring Flip Flop memories and beyond: training Recurrent Neural Networks with key insights.Frontiers in systems neuroscience · 2024Article
- Beyond spiking networks: The computational advantages of dendritic amplification and input segregation.Proceedings of the National Academy of Sciences of the United States of America · 2023Article
- Simulations approaching data: cortical slow waves in inferred models of the whole hemisphere of mouse.Communications biology · 2023Article
- Article
- Different eigenvalue distributions encode the same temporal tasks in recurrent neural networks.Cognitive neurodynamics · 2023Article
- A scalable implementation of the recursive least-squares algorithm for training spiking neural networks.Frontiers in neuroinformatics · 2023Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
5 authors.
Funding
Abstract
Trained recurrent networks are powerful tools for modeling dynamic neural computations. We present a target-based method for modifying the full connectivity matrix of a recurrent network to train it to perform tasks involving temporally complex input/output transformations. The method introduces a second network during training to provide suitable "target" dynamics useful for performing the task. Because it exploits the full recurrent connectivity, the method produces networks that perform tasks with fewer neurons and greater noise robustness than traditional least-squares (FORCE) approaches. In addition, we show how introducing additional input signals into the target-generating network, which act as task hints, greatly extends the range of tasks that can be learned and provides control over the complexity and nature of the dynamics of the trained, task-performing network.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.