Adrian Erasmus
Biographic Data
| ID | 1120537 |
|---|---|
| NAME | Adrian Erasmus |
| GIVEN NAMES | Adrian |
| FAMILY NAME | Erasmus |
| SIGNATURE | ERASMUS A |
| AFFILIATIONS | University of Alabama |
| ORCID | 0000-0001-8944-1598 |
| VERIFIED | Yes |
| TOTAL WORKS | 5 |
| TOTAL CITATIONS | 1 |
| WORKS AS AUTHOR | 5 |
| WORKS AS EDITOR | 0 |
| FIRST PUBLICATION YEAR | 2021 |
| LATEST PUBLICATION YEAR | 2026 |
| H-INDEX | 1 |
A goal-directed approach to disease classification
Disease classification plays an important role in numerous medical goals, from improving communication between researchers, physicians, and insurers to diagnosis and therapeutic prediction. Therefore, it's important to understand the principles behind our classificatory practices with a view to adopting the approach to disease classification that best serves the practical interests of medical science. In this paper, I discuss three prominent appr…
P-Hacking
The Bias Dynamics Model
Inferences from clinical research results to estimates of therapeutic effectiveness suffer due to various biases. I argue that predictions of medical effectiveness are prone to failure because current medical research overlooks the impacts of a particularly detrimental set of biases: meta-biases. Meta-biases are linked to higher-level characteristics of medical research and their effects are only observed when comparing sets of studies that share…
Interpretability and Unification
What is Interpretability
We argue that artificial networks are explainable and offer a novel theory of interpretability. Two sets of conceptual questions are prominent in theoretical engagements with artificial neural networks, especially in the context of medical artificial intelligence: (1) Are networks explainable , and if so, what does it mean to explain the output of a network? And (2) what does it mean for a network to be interpretable ? We argue that accounts of “…
The Bias Dynamics Model
Inferences from clinical research results to estimates of therapeutic effectiveness suffer due to various biases. I argue that predictions of medical effectiveness are prone to failure because current medical research overlooks the impacts of a particularly detrimental set of biases: meta-biases. Meta-biases are linked to higher-level characteristics of medical research and their effects are only observed when comparing sets of studies that share…
What is Interpretability
We argue that artificial networks are explainable and offer a novel theory of interpretability. Two sets of conceptual questions are prominent in theoretical engagements with artificial neural networks, especially in the context of medical artificial intelligence: (1) Are networks explainable , and if so, what does it mean to explain the output of a network? And (2) what does it mean for a network to be interpretable ? We argue that accounts of “…
Interpretability and Unification
The Bias Dynamics Model
Inferences from clinical research results to estimates of therapeutic effectiveness suffer due to various biases. I argue that predictions of medical effectiveness are prone to failure because current medical research overlooks the impacts of a particularly detrimental set of biases: meta-biases. Meta-biases are linked to higher-level characteristics of medical research and their effects are only observed when comparing sets of studies that share…
P-Hacking
A goal-directed approach to disease classification
Disease classification plays an important role in numerous medical goals, from improving communication between researchers, physicians, and insurers to diagnosis and therapeutic prediction. Therefore, it's important to understand the principles behind our classificatory practices with a view to adopting the approach to disease classification that best serves the practical interests of medical science. In this paper, I discuss three prominent appr…
Computer Science (4 works) · Epistemology (3 works) · Philosophy (3 works) · Artificial Intelligence (2 works) · Artificial neural network (2 works) · Cognitive science (2 works) · Explainable Artificial Intelligence (XAI (2 works) · Interpretability (2 works) · Psychology (2 works) · Advanced Malware Detection Techniques (1 work)