Overview: The Effect Propagation Process Motivation Non-Euclidean representation Non-linear time No a-priori causal structures Why Existing Methods Struggle? Why a new philosophy of causality? History of Causality The impact of Quantum Gravity on Causality Causality as Effect Propagation Process The Teleology of the Effect Propagation Process The Ontology of the Effect Propagation Process The Epistemology of the Effect Propagation Process Causal Emergence Contrast Validity Internal validity External validity Conclusion About Overview: The Effect Propagation Process The study of causality dates back to Aristotle and was later formalized in its commonly known form by Seneca. Seneca’s assumption of a background space and time was later challenged by relationalists like Leibniz and critiqued scientifically by Russell.
The author of DeepCausality has a background in Fintech and spent considerable time modeling market volatility. Market volatility modeling can be done in one of two ways. Mathematical models are still considered the gold standard, and many institutions operate them in production. Because markets work on time-series data, quantitative analysts (quants) use many time-series statistical techniques (ARIMA) combined with various differential equations. While these models are complex and require substantial optimization and computational power, they are robust and reliable in operations.
Overview Four layers of causal reasoning Observations Assumptions Inference Causality Core Architecture Context architecture Implementation principles About Overview DeepCausality follows a first principal architecture combined with a handful implementation principles to achieve a high degree of functionality with efficient and straightforward implementation. DeepCausality’s architecture uses the four layers of causal reasoning to achieve these goals.
Four layers of causal reasoning Conceptually, causal reasoning relies on four pillars: observations, assumptions, inferences, and causes, as depicted in the diagram below.
Data Context Temporal and Spatial Context Adjustable Temporal and Spatial Context About DeepCausality enables context aware causality reason across data-like, time-like, space-like, and spacetime-like entities stored within a context-hyper-graphs. Fundamentally, this allows scalable contextualization up to four dimensions.
Data Context The most basic form of contextualization adds more data to a model. For example, when modeling GDP for any country, commodity prices such as oil play a significant role in addition to several national factors. Conventionally, the GDP model separates internal from external factors to isolate systematic risk. DeepCausality solves this by adding two distinct data contexts, one for national data, i.e., population growth & manufacturing output, and a second context for data from external factors, i.e., standard crude oil price.
Overview Context Relations between data Conceptualization of time, space, and spacetime Data Time Space SpaceTime Structural conceptualization of causation Transparent composability Non-Euclidian data representation About Overview DeepCausality is a hyper-geometric computational causality library that enables fast and deterministic context-aware causal reasoning. Unique to DeepCausality is its ability to contextualize causal models, allowing causal reasoning over data from multiple external sources aggregated into one context. Beyond that, DeepCausality contributes several novel concepts to computational causality:
Overview Neuronal Nets The universal approximation theorem Independent and identically distributed data (IID) assumption Beyond the IID The gap Lack of context Lack of relations between data Lack of conceptualization of time and space Lack of structural conceptualization of causation Lack of non-Euclidian data representation Lack of transparent composability About Overview With the advent of advanced large language models, many new opportunities arise for applied artificial intelligence, but some challenges are becoming apparent. ChatGPT still hallucinates by fabricating text documented in a growing list of blunders. Beyond language models, there is a real discrepancy between the very high accuracy at which deep learning can detect and classify patterns and its utter incapability of discerning whether a detected pattern has any meaning.
Overview What is computational causality? Why Rust? What is DeepCausality? Hypergeometry Context Contextual causal reasoning End-to-end explainability Causal State Machines What can you do with DeepCausality? Contextualized streaming data Financial modelling Dynamic control systems Combined deep causality learning Limitations About Overview DeepCausality is a hyper-geometric computational causality library that enables fast and deterministic context aware causal reasoning. Deep causality offers multiple benefits such as fast reasoning, low-cost operations due to low computational requirements, the ability to analyse numerous data feeds in real-time, and even reasoning across data that changes over time, space, and spacetime through an adjustable context.
