it:ai_courses

artificial intelligence courses

Introduction

  • general pre-requisites are:
    • healthcare knowledge base
    • Python programming
      • Read, understand, and write code in Python, including language constructs such as functions and classes.
      • Read code using vectorized operations with the NumPy library.
    • probability theory
    • single variable calculus
    • vectors and matrices
    • machine learning
      • Build a machine learning model for a supervised learning problem and understand basic methods to represent categorical and numerical features as inputs for this model
      • Perform simple machine learning tasks, such as classification and regression, from a set of features
      • Apply basic knowledge of Python data and machine learning frameworks (Pandas, NumPy, TensorFlow, PyTorch) to manipulate and clean data for consumption by different estimators/algorithms (e.g. CNNs, RNNs, tree-based models).
  • syllabus may include:
    • clinical data
    • clinical knowledge systems such as physiologic time series, differential diagnosis, disease progression and modelling
    • risk stratification
    • survival modelling
    • Clinical Natural Language Processing
    • Causal Inference from Observational Data
    • AI risks
      • algorithmic bias
      • difficulty of generalizing AI models
    • use case examples
      • diagnosis
      • precision medicine - patient-centric care
      • prediction models

Online short courses 2023

it/ai_courses.txt · Last modified: 2023/03/24 07:26 by gary1

Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki