{"query": "Neural computation — networks that learn", "count": 20, "results": [{"id": "card_mind_neural_computation", "title": "Neural computation — networks that learn", "shelf": "codex", "surface": "secular", "snippet": "A neuron sums weighted inputs and fires past a threshold; networks of them learn, represent and predict. The brain is an information processor, which is why artificial neural networks borrow its shape", "authority_tier": "engine_derived", "source": "Narrow Highway — the mind", "readable": false, "generated": false}, {"id": "card_theory_neuromuscular_size_principle", "title": "Neuromuscular recruitment & the size principle (Henneman)", "shelf": "theories", "surface": "secular", "snippet": "Neuromuscular recruitment & the size principle (Henneman) — an engine domain that can touch it: exercise_science. Calibration: partial — specific relations verify; the theory as a whole is not a seala", "authority_tier": "reference", "source": "The Theory Assay — calibrated, not judged (lone-domain seeding)", "readable": false, "generated": false}, {"id": "card_theory_optimization", "title": "Optimization & gradient descent (following the slope)", "shelf": "theories", "surface": "secular", "snippet": "Optimization & gradient descent (following the slope) — an engine domain that can touch it: mathematics. Calibration: seals — gradients, step updates and convexity conditions compute. Find the input t", "authority_tier": "reference", "source": "The Theory Assay — calibrated, not judged (docs/THEORY_CATALOG.md)", "readable": false, "generated": false}, {"id": "card_bridge_master_boltzmann_factor", "title": "Master equation: n ~ e^(-E / kT)", "shelf": "bridges", "surface": "secular", "snippet": "the fraction of a system with energy E falls off exponentially against thermal energy kT. ONE equation, 5 domains, connected by a change of variable: meteorology [E = m g h — the barometric formula is", "authority_tier": "reference", "source": "The Bridges — cross-domain isomorphisms", "readable": false, "generated": false}, {"id": "card_src_openstax_principles_data_science_7_1_introduction_to_neural_networks_30c869bc", "title": "7.1 Introduction to Neural Networks — Principles of Data Science", "shelf": "reference", "surface": "secular", "snippet": "7.1\n\nIntroduction to Neural Networks\n\nLearning Outcomes\n\nBy the end of this section, you should be able to:\n\n7.1.1\nDefine neural networks and discuss the types of problems for which they may be useful", "authority_tier": "reference", "source": "OpenStax: Principles of Data Science (CC-BY 4.0)", "readable": false, "generated": false}, {"id": "card_src_word_neural_network", "title": "neural network", "shelf": "dictionary", "surface": "secular", "snippet": "neural network: (noun) computer architecture in which processors are connected in a manner suggestive of connections between neurons; can learn by trial and error — syn: neural net · (noun) any networ", "authority_tier": "reference", "source": "WordNet 3.0, Princeton University (WordNet License)", "readable": false, "generated": false}, {"id": "card_src_word_neural_net", "title": "neural net", "shelf": "dictionary", "surface": "secular", "snippet": "neural net: (noun) computer architecture in which processors are connected in a manner suggestive of connections between neurons; can learn by trial and error — syn: neural network · (noun) any networ", "authority_tier": "reference", "source": "WordNet 3.0, Princeton University (WordNet License)", "readable": false, "generated": false}, {"id": "card_src_openstax_introduction_behavioral_neuroscience_2_2_neural_circuits_8b9eb82a", "title": "2.2 Neural Circuits — Introduction to Behavioral Neuroscience", "shelf": "reference", "surface": "secular", "snippet": "2.2\n\nNeural Circuits\n\nLearning Objectives\n\nBy the end of this section, you should be able to\n\n2.2.1\nDescribe the rhythmic behavior produced by the simple swim circuit in Tritonia diomedea.\n\n2.2.2\nDefi", "authority_tier": "reference", "source": "OpenStax: Introduction to Behavioral Neuroscience (CC-BY 4.0)", "readable": false, "generated": false}, {"id": "card_src_openstax_principles_data_science_7_3_introduction_to_deep_learning_819494d1", "title": "7.3 Introduction to Deep Learning — Principles of Data Science", "shelf": "reference", "surface": "secular", "snippet": "7.3\n\nIntroduction to Deep Learning\n\nLearning Outcomes\n\nBy the end of this section, you should be able to:\n\n7.3.1\nDiscuss the role of hidden layers in a neural network.\n\n7.3.2\nDescribe loss/error funct", "authority_tier": "reference", "source": "OpenStax: Principles of Data Science (CC-BY 4.0)", "readable": false, "generated": false}, {"id": "card_src_etym_neural", "title": "neural", "shelf": "etymology", "surface": "secular", "snippet": "neural: etymology (Webster 1913) — a.: [Gr. (Anat. & Zoöl.) Defn: relating to the nerves or nervous system; taining to, situated in the region of, or on the side with, the neural, or cerebro-spinal, a", "authority_tier": "reference", "source": "Webster's Revised Unabridged Dictionary (1913), Project Gutenberg eBook #29765 — public domain", "readable": true, "generated": false}, {"id": "card_calc_cnn_layer", "title": "Convolutional neural network layer", "shelf": "calculations", "surface": "secular", "snippet": "Convolutional neural network layer — computer_science. Formula: feature = input * filter. Canonical FORM: convolution ((f*g)(t) = integral f(tau) g(t-tau) dtau) — vision models learn the filters they ", "authority_tier": "reference", "source": "The Calculation Map — every calculation, mapped by form", "readable": false, "generated": false}, {"id": "card_calc_td_learning", "title": "Temporal-difference learning", "shelf": "calculations", "surface": "secular", "snippet": "Temporal-difference learning — computer_science. Formula: V(s) <- V(s) + alpha [ r + gamma V(s') - V(s) ]. Canonical FORM: recursion (x_{n+1} = f(x_n)) — learn the value function from experience by bo", "authority_tier": "reference", "source": "The Calculation Map — every calculation, mapped by form", "readable": false, "generated": false}, {"id": "card_src_openstax_introduction_computer_science_labs_041ec639", "title": "Labs — Introduction to Computer Science", "shelf": "reference", "surface": "secular", "snippet": "Labs\n\n1\n.\n\nExplore the Parable of the Polygons. How does computer science contribute to the simulation? What does the simulation suggest is needed in the world? What are the limitations of the simulat", "authority_tier": "reference", "source": "OpenStax: Introduction to Computer Science (CC-BY 4.0)", "readable": false, "generated": false}, {"id": "card_bridge_master_bellman_value", "title": "Master equation: V*(s) = max_a [ R(s,a) + gamma * sum_s' P(s'|s,a) V*(s') ]", "shelf": "bridges", "surface": "secular", "snippet": "how to act well across time: the worth of where you stand is the best you can do now plus the discounted worth of where that lands you. Reinforcement learning learns it from experience; optimal contro", "authority_tier": "reference", "source": "The Bridges — cross-domain isomorphisms", "readable": false, "generated": false}, {"id": "card_src_openstax_principles_data_science_key_terms_fe7210fc", "title": "Key Terms — Principles of Data Science", "shelf": "reference", "surface": "secular", "snippet": "Key Terms\n\nactivation for a neuron, the process of sending an output signal after having received appropriate input signals\n\nactivation function non-decreasing function f that determines whether the n", "authority_tier": "reference", "source": "OpenStax: Principles of Data Science (CC-BY 4.0)", "readable": false, "generated": false}, {"id": "card_src_etym_epineural", "title": "epineural", "shelf": "etymology", "surface": "secular", "snippet": "epineural: etymology (Webster 1913) — a.: [Pref. epi- + neural.]. From Webster's Revised Unabridged Dictionary (1913), public domain.", "authority_tier": "reference", "source": "Webster's Revised Unabridged Dictionary (1913), Project Gutenberg eBook #29765 — public domain", "readable": true, "generated": false}, {"id": "card_c_305b16a890ad", "title": "Pheromones — the molecule is the message ↔ The radio spectrum — one law from the cavity", "shelf": "connections", "surface": null, "snippet": "Radio waves (EM), DNA (genetic), morphemes (linguistic), neurotransmitters (neural), and the sealed receipt of this very engine (cryptographic) are all the same abstraction — Shannon's channel.  — a c", "authority_tier": "engine_derived", "source": "Concordance miner — 2026-07-11", "readable": false, "generated": false}, {"id": "card_c_9a732b4ecc5d", "title": "Pheromones — the molecule is the message ↔ The genome as information — and the algebra ", "shelf": "connections", "surface": null, "snippet": "Radio waves (EM), DNA (genetic), morphemes (linguistic), neurotransmitters (neural), and the sealed receipt of this very engine (cryptographic) are all the same abstraction — Shannon's channel.  — a c", "authority_tier": "engine_derived", "source": "Concordance miner — 2026-07-11", "readable": false, "generated": false}, {"id": "card_src_etym_zygosphene", "title": "zygosphene", "shelf": "etymology", "surface": "secular", "snippet": "zygosphene: etymology (Webster 1913) — n.: [Gr. (Anat.) Defn: A median process on the front part of the neural arch of the vertebræ of most snakes and some lizards, which fits into a fossa, called the", "authority_tier": "reference", "source": "Webster's Revised Unabridged Dictionary (1913), Project Gutenberg eBook #29765 — public domain", "readable": true, "generated": false}, {"id": "card_k_ncs_validation", "title": "Nested Control Systems — a pre-registered falsification program (NHANES)", "shelf": "science", "surface": "secular", "snippet": "STATUS: pre-registered protocol, frozen 2026-03-04 — NOT yet executed. No verdict is claimed; this seed records the TEST, not a result.\nThe nested-control-systems framework (the autonomic spine) is bo", "authority_tier": "matt", "source": "Operator's artifact (Matt) — framework_validation_v3_final, frozen 2026-03-04", "readable": false, "generated": false}], "house": {"door": "FIND", "kind": "cards", "trail": "results", "seal": null, "next_step": {"do": "open the top card", "door": "FIND", "tool": "card_get", "params": {"id": "card_mind_neural_computation"}}, "ends": "a verdict or a card · the trail · a seal · one next step"}}