feat: collapsible expansion, canonical formalism pages, citation enrichment

formalisms.yaml

@@ -0,0 +1,815 @@
+formalisms:
+- id: pca
+  name: Principal Component Analysis
+  year: 1901
+  origin: Pearson; Hotelling (1933)
+  signature:
+    operation: project
+    domain: vector
+    codomain: vector
+    objective_family: none
+  meso_type: linear_projection
+  macro_type: eigenvalue_problem
+  canonical_reference: Pearson, K. (1901). On lines and planes of closest fit.
+  status: seed
+- id: cca
+  name: Canonical Correlation Analysis
+  year: 1936
+  origin: Hotelling
+  signature:
+    operation: project
+    domain: vector
+    codomain: vector
+    objective_family: correlation
+  meso_type: joint_embedding
+  macro_type: eigenvalue_problem
+  canonical_reference: Hotelling, H. (1936). Relations between two sets of variates.
+  status: seed
+- id: kernel_cca
+  name: Kernel Canonical Correlation Analysis
+  year: 2002
+  origin: Bach & Jordan
+  signature:
+    operation: project
+    domain: vector
+    codomain: vector
+    objective_family: correlation
+  meso_type: kernel_method
+  macro_type: eigenvalue_problem
+  canonical_reference: Bach, F.R. & Jordan, M.I. (2002). Kernel independent component analysis. JMLR.
+  status: seed
+- id: ica
+  name: Independent Component Analysis
+  year: 1994
+  origin: Comon
+  signature:
+    operation: decompose
+    domain: vector
+    codomain: vector
+    objective_family: information
+  meso_type: linear_projection
+  macro_type: optimization
+  canonical_reference: Comon, P. (1994). Independent component analysis, a new concept?
+  status: seed
+- id: fisher_lda
+  name: Fisher Linear Discriminant Analysis
+  year: 1936
+  origin: Fisher
+  signature:
+    operation: project
+    domain: vector
+    codomain: vector
+    objective_family: none
+  meso_type: linear_projection
+  macro_type: eigenvalue_problem
+  canonical_reference: Fisher, R.A. (1936). The use of multiple measurements in taxonomic problems.
+  status: seed
+- id: mds
+  name: Multi-Dimensional Scaling
+  year: 1952
+  origin: Torgerson
+  signature:
+    operation: project
+    domain: matrix
+    codomain: vector
+    objective_family: none
+  meso_type: spectral_method
+  macro_type: eigenvalue_problem
+  canonical_reference: 'Torgerson, W.S. (1952). Multidimensional scaling: I. Theory and method.'
+  status: seed
+- id: isomap
+  name: Isometric Feature Mapping
+  year: 2000
+  origin: Tenenbaum, de Silva & Langford
+  signature:
+    operation: project
+    domain: manifold
+    codomain: vector
+    objective_family: none
+  meso_type: spectral_method
+  macro_type: eigenvalue_problem
+  canonical_reference: Tenenbaum, J.B., de Silva, V., & Langford, J.C. (2000). A global geometric framework for nonlinear
+    dimensionality reduction. Science.
+  status: seed
+- id: lle
+  name: Locally Linear Embedding
+  year: 2000
+  origin: Roweis & Saul
+  signature:
+    operation: project
+    domain: manifold
+    codomain: vector
+    objective_family: none
+  meso_type: spectral_method
+  macro_type: eigenvalue_problem
+  canonical_reference: Roweis, S.T. & Saul, L.K. (2000). Nonlinear dimensionality reduction by locally linear embedding. Science.
+  status: seed
+- id: laplacian_eigenmaps
+  name: Laplacian Eigenmaps
+  year: 2003
+  origin: Belkin & Niyogi
+  signature:
+    operation: project
+    domain: manifold
+    codomain: vector
+    objective_family: energy
+  meso_type: spectral_method
+  macro_type: eigenvalue_problem
+  canonical_reference: Belkin, M. & Niyogi, P. (2003). Laplacian eigenmaps for dimensionality reduction and data representation.
+    Neural Computation.
+  researchor_artifact_id: laplacian_matrix
+  status: seed
+- id: svd
+  name: Singular Value Decomposition
+  year: 1873
+  origin: Beltrami; Jordan; Golub & Reinsch
+  signature:
+    operation: decompose
+    domain: matrix
+    codomain: matrix
+    objective_family: none
+  meso_type: linear_projection
+  macro_type: eigenvalue_problem
+  canonical_reference: Golub, G.H. & Reinsch, C. (1970). Singular value decomposition and least squares solutions.
+  researchor_artifact_id: singular_value_decomposition
+  status: seed
+- id: nmf
+  name: Non-negative Matrix Factorization
+  year: 1999
+  origin: Lee & Seung
+  signature:
+    operation: decompose
+    domain: matrix
+    codomain: matrix
+    objective_family: divergence
+  meso_type: linear_projection
+  macro_type: optimization
+  canonical_reference: Lee, D.D. & Seung, H.S. (1999). Learning the parts of objects by non-negative matrix factorization.
+    Nature.
+  status: seed
+  canonical_arxiv_id: 0408058
+- id: kernel_pca
+  name: Kernel Principal Component Analysis
+  year: 1998
+  origin: Schölkopf, Smola & Müller
+  signature:
+    operation: project
+    domain: vector
+    codomain: vector
+    objective_family: none
+  meso_type: kernel_method
+  macro_type: eigenvalue_problem
+  canonical_reference: Schölkopf, B., Smola, A., & Müller, K.-R. (1998). Nonlinear component analysis as a kernel eigenvalue
+    problem. Neural Computation.
+  status: seed
+- id: kernel_ridge_regression
+  name: Kernel Ridge Regression
+  year: 1998
+  origin: Saunders, Gammerman & Vovk; extended by many
+  signature:
+    operation: transform
+    domain: vector
+    codomain: scalar
+    objective_family: none
+  meso_type: kernel_method
+  macro_type: optimization
+  canonical_reference: Saunders, C., Gammerman, A., & Vovk, V. (1998). Ridge regression learning algorithm in dual variables.
+    ICML.
+  status: seed
+- id: gaussian_process
+  name: Gaussian Process Regression
+  year: 1996
+  origin: Williams & Rasmussen; roots in kriging (Matheron 1963)
+  signature:
+    operation: transform
+    domain: vector
+    codomain: distribution
+    objective_family: likelihood
+  meso_type: kernel_method
+  macro_type: statistical_inference
+  canonical_reference: Rasmussen, C.E. & Williams, C.K.I. (2006). Gaussian Processes for Machine Learning. MIT Press.
+  status: seed
+- id: svm
+  name: Support Vector Machine
+  year: 1995
+  origin: Cortes & Vapnik
+  signature:
+    operation: transform
+    domain: vector
+    codomain: assignment
+    objective_family: none
+  meso_type: kernel_method
+  macro_type: optimization
+  canonical_reference: Cortes, C. & Vapnik, V. (1995). Support-vector networks. Machine Learning.
+  status: seed
+- id: mmd
+  name: Maximum Mean Discrepancy
+  year: 2006
+  origin: Gretton, Borgwardt, Rasch, Schölkopf & Smola
+  signature:
+    operation: match
+    domain: distribution
+    codomain: scalar
+    objective_family: none
+  meso_type: kernel_method
+  macro_type: statistical_inference
+  canonical_reference: Gretton, A. et al. (2012). A kernel two-sample test. JMLR.
+  status: seed
+- id: kl_divergence_min
+  name: KL Divergence Minimization
+  year: 1951
+  origin: Kullback & Leibler
+  signature:
+    operation: minimize
+    domain: distribution
+    codomain: distribution
+    objective_family: divergence
+  meso_type: information_geometry
+  macro_type: optimization
+  canonical_reference: Kullback, S. & Leibler, R.A. (1951). On information and sufficiency.
+  researchor_artifact_id: relative_entropy
+  status: seed
+- id: mutual_info_max
+  name: Mutual Information Maximization
+  year: 1948
+  origin: Shannon; McGill (1954)
+  signature:
+    operation: maximize
+    domain: distribution
+    codomain: scalar
+    objective_family: information
+  meso_type: information_geometry
+  macro_type: optimization
+  canonical_reference: Shannon, C.E. (1948). A mathematical theory of communication.
+  researchor_artifact_id: mutual_information
+  status: seed
+- id: cross_entropy_min
+  name: Cross-Entropy Minimization
+  year: 1948
+  origin: Shannon; Good (1956)
+  signature:
+    operation: minimize
+    domain: distribution
+    codomain: distribution
+    objective_family: divergence
+  meso_type: information_geometry
+  macro_type: optimization
+  canonical_reference: Good, I.J. (1956). The population frequencies of species and the estimation of population parameters.
+  researchor_artifact_id: entropy
+  status: seed
+- id: infonce
+  name: InfoNCE / Contrastive Estimation
+  year: 2018
+  origin: van den Oord, Li & Vinyals
+  signature:
+    operation: maximize
+    domain: vector
+    codomain: scalar
+    objective_family: information
+  meso_type: joint_embedding
+  macro_type: optimization
+  canonical_reference: van den Oord, A., Li, Y., & Vinyals, O. (2018). Representation learning with contrastive predictive
+    coding. arXiv:1807.03748.
+  status: seed
+  canonical_arxiv_id: '1807.03748'
+- id: js_divergence
+  name: Jensen-Shannon Divergence
+  year: 1991
+  origin: Lin; extended from KL
+  signature:
+    operation: match
+    domain: distribution
+    codomain: scalar
+    objective_family: divergence
+  meso_type: information_geometry
+  macro_type: statistical_inference
+  canonical_reference: Lin, J. (1991). Divergence measures based on the Shannon entropy. IEEE Trans. Info. Theory.
+  status: seed
+- id: elbo
+  name: Evidence Lower BOund Maximization
+  year: 1999
+  origin: Jordan, Ghahramani, Jaakkola & Saul; variational Bayes
+  signature:
+    operation: maximize
+    domain: distribution
+    codomain: distribution
+    objective_family: divergence
+  meso_type: variational
+  macro_type: optimization
+  canonical_reference: Jordan, M.I. et al. (1999). An introduction to variational methods for graphical models. Machine Learning.
+  status: seed
+  canonical_arxiv_id: '1312.6114'
+- id: variational_inference
+  name: Variational Inference
+  year: 1990
+  origin: Hinton & van Camp; Jordan et al.; Wainwright & Jordan
+  signature:
+    operation: minimize
+    domain: distribution
+    codomain: distribution
+    objective_family: divergence
+  meso_type: variational
+  macro_type: statistical_inference
+  canonical_reference: Wainwright, M.J. & Jordan, M.I. (2008). Graphical models, exponential families, and variational inference.
+    Foundations & Trends in ML.
+  status: seed
+- id: mean_field
+  name: Mean-Field Approximation
+  year: 1937
+  origin: Landau; Weiss; applied to stat mech and later VI
+  signature:
+    operation: minimize
+    domain: distribution
+    codomain: distribution
+    objective_family: divergence
+  meso_type: mean_field
+  macro_type: statistical_inference
+  canonical_reference: Parisi, G. (1988). Statistical Field Theory. Addison-Wesley.
+  status: seed
+- id: mle
+  name: Maximum Likelihood Estimation
+  year: 1922
+  origin: Fisher
+  signature:
+    operation: maximize
+    domain: distribution
+    codomain: scalar
+    objective_family: likelihood
+  meso_type: probabilistic_inference
+  macro_type: statistical_inference
+  canonical_reference: Fisher, R.A. (1922). On the mathematical foundations of theoretical statistics.
+  status: seed
+- id: map_estimation
+  name: Maximum A Posteriori Estimation
+  year: 1763
+  origin: Bayes; Laplace
+  signature:
+    operation: maximize
+    domain: distribution
+    codomain: scalar
+    objective_family: likelihood
+  meso_type: probabilistic_inference
+  macro_type: statistical_inference
+  canonical_reference: Berger, J.O. (1985). Statistical Decision Theory and Bayesian Analysis. Springer.
+  status: seed
+- id: em_algorithm
+  name: Expectation-Maximization
+  year: 1977
+  origin: Dempster, Laird & Rubin
+  signature:
+    operation: maximize
+    domain: distribution
+    codomain: distribution
+    objective_family: likelihood
+  meso_type: variational
+  macro_type: optimization
+  canonical_reference: Dempster, A.P., Laird, N.M., & Rubin, D.B. (1977). Maximum likelihood from incomplete data via the
+    EM algorithm. JRSS-B.
+  status: seed
+- id: mcmc
+  name: Markov Chain Monte Carlo
+  year: 1953
+  origin: Metropolis, Rosenbluth, Rosenbluth, Teller & Teller; Hastings (1970)
+  signature:
+    operation: sample
+    domain: distribution
+    codomain: sequence
+    objective_family: none
+  meso_type: probabilistic_inference
+  macro_type: stochastic_process
+  canonical_reference: Metropolis, N. et al. (1953). Equation of state calculations by fast computing machines.
+  researchor_artifact_id: markov_chain
+  status: seed
+- id: empirical_bayes
+  name: Empirical Bayes / Type-II Maximum Likelihood
+  year: 1955
+  origin: Robbins; Efron & Morris
+  signature:
+    operation: maximize
+    domain: distribution
+    codomain: distribution
+    objective_family: likelihood
+  meso_type: probabilistic_inference
+  macro_type: statistical_inference
+  canonical_reference: Robbins, H. (1955). An empirical Bayes approach to statistics. Proc. Third Berkeley Symp.
+  status: seed
+- id: normalizing_flow
+  name: Normalizing Flow
+  year: 2015
+  origin: Rezende & Mohamed; Dinh, Krueger & Bengio (NICE 2014)
+  signature:
+    operation: transform
+    domain: distribution
+    codomain: distribution
+    objective_family: likelihood
+  meso_type: variational
+  macro_type: statistical_inference
+  canonical_reference: Rezende, D.J. & Mohamed, S. (2015). Variational inference with normalizing flows. ICML.
+  status: seed
+  canonical_arxiv_id: '1505.05770'
+- id: boltzmann_distribution
+  name: Boltzmann / Gibbs Distribution
+  year: 1868
+  origin: Boltzmann; Gibbs (1902)
+  signature:
+    operation: sample
+    domain: scalar_field
+    codomain: distribution
+    objective_family: energy
+  meso_type: energy_model
+  macro_type: hamiltonian_system
+  canonical_reference: Gibbs, J.W. (1902). Elementary Principles in Statistical Mechanics.
+  researchor_mental_model_id: ergodicity
+  status: seed
+- id: free_energy_min
+  name: Free Energy Minimization
+  year: 1873
+  origin: Helmholtz; Gibbs
+  signature:
+    operation: minimize
+    domain: distribution
+    codomain: distribution
+    objective_family: energy
+  meso_type: energy_model
+  macro_type: hamiltonian_system
+  canonical_reference: Helmholtz, H. (1882). Die Thermodynamik chemischer Vorgänge.
+  researchor_mental_model_id: phase_transitions
+  status: seed
+- id: hopfield_network
+  name: Hopfield Network / Spin Glass
+  year: 1982
+  origin: Hopfield; Sherrington & Kirkpatrick (1975 spin glass)
+  signature:
+    operation: minimize
+    domain: vector
+    codomain: assignment
+    objective_family: energy
+  meso_type: spin_system
+  macro_type: hamiltonian_system
+  canonical_reference: Hopfield, J.J. (1982). Neural networks and physical systems with emergent collective computational
+    abilities. PNAS.
+  researchor_mental_model_id: attractors_and_basins
+  status: seed
+- id: renormalization_group
+  name: Renormalization Group
+  year: 1971
+  origin: Wilson; Kadanoff (block-spin 1966)
+  signature:
+    operation: transform
+    domain: scalar_field
+    codomain: scalar_field
+    objective_family: none
+  meso_type: energy_model
+  macro_type: hamiltonian_system
+  canonical_reference: Wilson, K.G. (1971). Renormalization group and critical phenomena. Phys. Rev. B.
+  researchor_mental_model_id: scale_invariance
+  status: seed
+- id: langevin_dynamics
+  name: Langevin Dynamics
+  year: 1908
+  origin: Langevin; adapted to sampling by Parisi (1981)
+  signature:
+    operation: sample
+    domain: scalar_field
+    codomain: distribution
+    objective_family: energy
+  meso_type: dynamical_system
+  macro_type: stochastic_process
+  canonical_reference: Langevin, P. (1908). Sur la théorie du mouvement brownien.
+  researchor_artifact_id: brownian_motion
+  status: seed
+- id: hamiltonian_monte_carlo
+  name: Hamiltonian Monte Carlo
+  year: 1987
+  origin: Duane, Kennedy, Pendleton & Roweth; Neal (2011 MCMC handbook)
+  signature:
+    operation: sample
+    domain: distribution
+    codomain: sequence
+    objective_family: energy
+  meso_type: dynamical_system
+  macro_type: hamiltonian_system
+  canonical_reference: Neal, R.M. (2011). MCMC using Hamiltonian dynamics. Handbook of Markov Chain Monte Carlo.
+  status: seed
+- id: diffusion_sde
+  name: Diffusion Process / Reverse-Time SDE
+  year: 2015
+  origin: Sohl-Dickstein et al.; Ho, Jain & Abbeel (DDPM 2020); Song et al. (SDE 2021)
+  signature:
+    operation: sample
+    domain: distribution
+    codomain: distribution
+    objective_family: none
+  meso_type: diffusion_process
+  macro_type: stochastic_process
+  canonical_reference: Song, Y. et al. (2021). Score-based generative modeling through stochastic differential equations.
+    ICLR.
+  researchor_artifact_id: brownian_motion
+  researchor_mental_model_id: irreversibility
+  status: seed
+  canonical_arxiv_id: '2011.13456'
+- id: wasserstein_distance
+  name: Wasserstein Distance / Earth Mover's Distance
+  year: 1781
+  origin: Monge; Kantorovich (1942)
+  signature:
+    operation: match
+    domain: distribution
+    codomain: scalar
+    objective_family: none
+  meso_type: optimal_transport
+  macro_type: optimization
+  canonical_reference: Kantorovich, L.V. (1942). On the translocation of masses.
+  status: seed
+- id: sinkhorn_algorithm
+  name: Sinkhorn-Knopp Algorithm / Entropic OT
+  year: 1967
+  origin: Sinkhorn & Knopp; Cuturi (2013) for ML
+  signature:
+    operation: match
+    domain: distribution
+    codomain: matrix
+    objective_family: divergence
+  meso_type: optimal_transport
+  macro_type: optimization
+  canonical_reference: 'Cuturi, M. (2013). Sinkhorn distances: lightspeed computation of optimal transport. NeurIPS.'
+  status: seed
+  canonical_arxiv_id: '1306.0895'
+- id: kantorovich_dual
+  name: Kantorovich Duality
+  year: 1942
+  origin: Kantorovich
+  signature:
+    operation: maximize
+    domain: distribution
+    codomain: scalar
+    objective_family: none
+  meso_type: optimal_transport
+  macro_type: optimization
+  canonical_reference: 'Villani, C. (2008). Optimal Transport: Old and New. Springer.'
+  status: seed
+- id: gradient_descent
+  name: Gradient Descent
+  year: 1847
+  origin: Cauchy
+  signature:
+    operation: minimize
+    domain: scalar_field
+    codomain: vector
+    objective_family: none
+  meso_type: none
+  macro_type: optimization
+  canonical_reference: Cauchy, A. (1847). Méthode générale pour la résolution des systèmes d'équations simultanées.
+  researchor_artifact_id: gradient_descent
+  status: seed
+- id: sgd
+  name: Stochastic Gradient Descent
+  year: 1951
+  origin: Robbins & Monro
+  signature:
+    operation: minimize
+    domain: scalar_field
+    codomain: vector
+    objective_family: none
+  meso_type: none
+  macro_type: optimization
+  canonical_reference: Robbins, H. & Monro, S. (1951). A stochastic approximation method.
+  researchor_artifact_id: stochastic_gradient_descent
+  status: seed
+- id: lagrange_multiplier
+  name: Constrained Optimization (Lagrange Multiplier)
+  year: 1788
+  origin: Lagrange
+  signature:
+    operation: minimize
+    domain: scalar_field
+    codomain: vector
+    objective_family: none
+  meso_type: none
+  macro_type: optimization
+  canonical_reference: Lagrange, J.-L. (1788). Mécanique Analytique.
+  status: seed
+- id: proximal_gradient
+  name: Proximal Gradient Method
+  year: 2005
+  origin: Combettes & Wajs; Beck & Teboulle (FISTA 2009)
+  signature:
+    operation: minimize
+    domain: scalar_field
+    codomain: vector
+    objective_family: none
+  meso_type: none
+  macro_type: optimization
+  canonical_reference: Beck, A. & Teboulle, M. (2009). A fast iterative shrinkage-thresholding algorithm. SIAM J. Imaging
+    Sci.
+  status: seed
+- id: adam
+  name: Adam Optimizer
+  year: 2014
+  origin: Kingma & Ba
+  signature:
+    operation: minimize
+    domain: scalar_field
+    codomain: vector
+    objective_family: none
+  meso_type: none
+  macro_type: optimization
+  canonical_reference: 'Kingma, D.P. & Ba, J. (2015). Adam: a method for stochastic optimization. ICLR.'
+  status: seed
+  canonical_arxiv_id: '1412.6980'
+- id: softmax_attention
+  name: Softmax Attention / Weighted Aggregation
+  year: 2014
+  origin: Bahdanau, Cho & Bengio; Vaswani et al. (Transformer 2017)
+  signature:
+    operation: aggregate
+    domain: sequence
+    codomain: vector
+    objective_family: none
+  meso_type: none
+  macro_type: none
+  canonical_reference: Vaswani, A. et al. (2017). Attention is all you need. NeurIPS.
+  status: seed
+  canonical_arxiv_id: '1706.03762'
+- id: residual_connection
+  name: Residual Connection / Skip Connection
+  year: 2016
+  origin: He, Zhang, Ren & Sun; earlier in Hochreiter & Schmidhuber (LSTM 1997)
+  signature:
+    operation: transform
+    domain: vector
+    codomain: vector
+    objective_family: none
+  meso_type: none
+  macro_type: none
+  canonical_reference: He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. CVPR.
+  status: seed
+  canonical_arxiv_id: '1512.03385'
+- id: batch_normalization
+  name: Batch Normalization
+  year: 2015
+  origin: Ioffe & Szegedy
+  signature:
+    operation: transform
+    domain: vector
+    codomain: vector
+    objective_family: none
+  meso_type: none
+  macro_type: none
+  canonical_reference: 'Ioffe, S. & Szegedy, C. (2015). Batch normalization: accelerating deep network training. ICML.'
+  status: seed
+  canonical_arxiv_id: '1502.03167'
+- id: vae
+  name: Variational Autoencoder
+  year: 2013
+  origin: Kingma & Welling; Rezende, Mohamed & Wierstra
+  signature:
+    operation: transform
+    domain: vector
+    codomain: distribution
+    objective_family: divergence
+  meso_type: variational
+  macro_type: statistical_inference
+  canonical_reference: Kingma, D.P. & Welling, M. (2014). Auto-encoding variational Bayes. ICLR.
+  status: seed
+  canonical_arxiv_id: '1312.6114'
+- id: gan
+  name: Generative Adversarial Network
+  year: 2014
+  origin: Goodfellow et al.
+  signature:
+    operation: minimize
+    domain: distribution
+    codomain: distribution
+    objective_family: adversarial
+  meso_type: game_theoretic
+  macro_type: optimization
+  canonical_reference: Goodfellow, I.J. et al. (2014). Generative adversarial nets. NeurIPS.
+  researchor_mental_model_id: nash_equilibrium
+  status: seed
+  canonical_arxiv_id: '1406.2661'
+- id: contrastive_learning
+  name: Contrastive Learning
+  year: 2005
+  origin: Chopra, Hadsell & LeCun (Siamese, 2005); Hadsell et al. (dimensionality reduction 2006)
+  signature:
+    operation: minimize
+    domain: vector
+    codomain: scalar
+    objective_family: energy
+  meso_type: joint_embedding
+  macro_type: optimization
+  canonical_reference: Hadsell, R., Chopra, S., & LeCun, Y. (2006). Dimensionality reduction by learning an invariant mapping.
+    CVPR.
+  researchor_mental_model_id: signal_vs_noise
+  status: seed
+- id: knowledge_distillation
+  name: Knowledge Distillation
+  year: 2015
+  origin: Hinton, Vinyals & Dean
+  signature:
+    operation: minimize
+    domain: distribution
+    codomain: distribution
+    objective_family: divergence
+  meso_type: none
+  macro_type: optimization
+  canonical_reference: Hinton, G., Vinyals, O., & Dean, J. (2015). Distilling the knowledge in a neural network. NeurIPS workshop.
+  status: seed
+  canonical_arxiv_id: '1503.02531'
+- id: layer_normalization
+  name: Layer Normalization
+  year: 2016
+  origin: Ba, Kiros & Hinton
+  signature:
+    operation: transform
+    domain: vector
+    codomain: vector
+    objective_family: none
+  meso_type: none
+  macro_type: none
+  canonical_reference: Ba, J.L., Kiros, J.R., & Hinton, G.E. (2016). Layer normalization. arXiv:1607.06450.
+  status: seed
+  canonical_arxiv_id: '1607.06450'
+- id: ridge_regression
+  name: Ridge Regression (L2 Regularization)
+  year: 1970
+  origin: Hoerl & Kennard; Tikhonov (1943)
+  signature:
+    operation: minimize
+    domain: vector
+    codomain: scalar
+    objective_family: none
+  meso_type: none
+  macro_type: optimization
+  canonical_reference: 'Hoerl, A.E. & Kennard, R.W. (1970). Ridge regression: biased estimation for nonorthogonal problems.'
+  status: seed
+- id: lasso
+  name: LASSO (L1 Regularization)
+  year: 1996
+  origin: Tibshirani
+  signature:
+    operation: minimize
+    domain: vector
+    codomain: scalar
+    objective_family: none
+  meso_type: none
+  macro_type: optimization
+  canonical_reference: Tibshirani, R. (1996). Regression shrinkage and selection via the lasso. JRSS-B.
+  status: seed
+- id: elastic_net
+  name: Elastic Net
+  year: 2005
+  origin: Zou & Hastie
+  signature:
+    operation: minimize
+    domain: vector
+    codomain: scalar
+    objective_family: none
+  meso_type: none
+  macro_type: optimization
+  canonical_reference: Zou, H. & Hastie, T. (2005). Regularization and variable selection via the elastic net. JRSS-B.
+  status: seed
+- id: spectral_clustering
+  name: Spectral Clustering
+  year: 2000
+  origin: Shi & Malik (normalized cuts); Ng, Jordan & Weiss (2002)
+  signature:
+    operation: decompose
+    domain: graph
+    codomain: assignment
+    objective_family: none
+  meso_type: spectral_method
+  macro_type: eigenvalue_problem
+  canonical_reference: 'Ng, A.Y., Jordan, M.I., & Weiss, Y. (2002). On spectral clustering: analysis and an algorithm. NeurIPS.'
+  researchor_artifact_id: laplacian_matrix
+  status: seed
+- id: pagerank
+  name: PageRank
+  year: 1998
+  origin: Page, Brin, Motwani & Winograd
+  signature:
+    operation: propagate
+    domain: graph
+    codomain: vector
+    objective_family: none
+  meso_type: spectral_method
+  macro_type: eigenvalue_problem
+  canonical_reference: 'Page, L. et al. (1999). The PageRank citation ranking: bringing order to the web.'
+  researchor_artifact_id: adjacency_matrix
+  researchor_mental_model_id: network_centrality
+  status: seed
+- id: fourier_transform
+  name: Fourier Transform / Spectral Decomposition
+  year: 1822
+  origin: Fourier; Cooley & Tukey (FFT 1965)
+  signature:
+    operation: decompose
+    domain: sequence
+    codomain: sequence
+    objective_family: none
+  meso_type: spectral_method
+  macro_type: none
+  canonical_reference: Fourier, J.B.J. (1822). Théorie analytique de la chaleur.
+  researchor_mental_model_id: signal_vs_noise
+  status: seed