minor changes for v2

01_intro.md

@@ -6,21 +6,21 @@ Welcome to the course! The course materials are a WORK IN PROGRESS. If you are u
 
 These lecture notes were written by <span style="color:orange">Elizaveta Semenova</span> (a.k.a. Liza). I am a lecturer in Biostatistics, Computational Epidemiology and Machine Learning at Imperial College London. My work is centered around scalable and flexible methods for spatiotemporal statistics and Bayesian machine learning using probabilsitic programming with applications in epidemiology. This course is meant to set you up well for doing similar research. 
 
-Most recently, my focus has been on using deep generative models to power MCMC inference in classical spatial statistics. It turns out that the same method works for a much wider range of applications, including disease transmission modelling! In part, this course does touch on these subjects. Feel free to reach out to discuss the landscape. 
+Most recently, my focus has been on using deep generative models to power MCMC inference in classical spatial statistics. It turns out that the same method works for a much wider range of applications, including disease transmission modelling! In part, this course does touch on these topics. Feel free to reach out to discuss the broader landscape of research. 
 
 More details about my work are available [here](https://www.elizaveta-semenova.com/).
 
 
 ## Giving feedback
 
-After the course, I plan to keep improving and expanding the materials since they will be helpful for future students and collaborators.
+After delivering the course, I plan to keep improving and expanding the materials since they will be helpful for future students and collaborators.
 
 - To correct typos, please make pull requests on [GitHub](https://github.com/elizavetasemenova/prob-epi). If these notes ever get published, I will list your name in Acknowledgements.
 
 - For more substantial suggestions about the course content, such as desired topics, please use issues on [GitHub](https://github.com/elizavetasemenova/prob-epi) or email them to `elizaveta [dot] p [dot] [insert my surname] [at] gmail [dot] com`.
 
 ```{margin}
-Acknowledging here that learning does not always have to be enjoyable.
+"and/or" is to acknowledge that learning does not always have to be enjoyable.
 ```
 - If you enjoyed the content **and / or** learnt from it, please leave a 'star' to the [book's GitHub](https://github.com/elizavetasemenova/prob-epi) repository. 
 
@@ -40,7 +40,7 @@ year = {2024}
 
 ## Conda environment
 
-To run the code examples from the course, the recommended Conda environment can be created as follows:
+To run the code examples from the course, you could either download separate notebooks and run them on Colab, or exxecute the notebooks locally. The recommended Conda environment can be created as follows:
 
 ```
 conda create -n aims python=3.9

02_about.md

@@ -8,13 +8,13 @@ This online book consists of lecture notes of the course which I taught during
 of MSc ["AI for Science"](https://ai.aims.ac.za/) at the [African Institute for Mathematical Sciences (AIMS)](https://aims.ac.za/), South Africa. 
 
 
-The title of the course for the first cohort was "Bayesian Modelling and Probabilistic Programming with Numpyro and examples from Epidemiology''.
+The title of the course for the first cohort was **"Bayesian Modelling and Probabilistic Programming with Numpyro and examples from Epidemiology''**.
 
-The title of the course for the second cohort is "Bayesian Modelling with Numpyro and Deep Generative Surrogates for Epidemiology''.
+The title of the course for the second cohort is **"Bayesian Modelling with Numpyro and Deep Generative Surrogates for Epidemiology''**.
 
 ## Abstract
 
-In this course we will explore a range of topics in Bayesian modelling, such as Bayesian inference, hierarchical modelling, Gaussian processes for spatial statistics, ordinary differential equations and agent-based models for disease transmission modelling. 
+In this course we will explore a range of topics in Bayesian modelling, such as Bayesian inference, hierarchical modelling, Gaussian processes for spatial statistics, ordinary differential equations (ODEs) and agent-based models (ABMs) for disease transmission modelling. 
 
 Using the probabilistic programming language `Numpyro`, we will construct probabilistic models and perform Bayesian inference to quantify uncertainty in model predictions and parameter estimates. 
 

03_intro_epi.md

@@ -9,7 +9,7 @@ Let's uncover each of the three key terms of the course - **epidemiology**, **Ba
 
 Epidemiology serves as the underlying rationale in this course, explaining <font color='orange'>WHY</font> we develop the probabilistic models we'll be examining. Essentially, it addresses the question: 'What real-world phenomena are we aiming to analyse using these models?'
 
-<font color='orange'>Epidemiology</font> studies human health. To be more specific, it is the study of how diseases and health-related events are distributed within populations and the factors that influence these distributions. It is a branch of public health that focuses on understanding the patterns, causes, and effects of diseases and health conditions on a large scale. Epidemiologists collect and analyse *data* to investigate the occurrence of health outcomes, their risk factors, and the impact of various interventions or preventive measures.
+<font color='orange'>Epidemiology</font> studies human health. To be more specific, it is the study of how diseases and health-related events are distributed within populations and the factors that influence these distributions. It is a branch of public health that focuses on understanding the patterns, causes, and effects of diseases and health conditions on a large scale. Epidemiologists collect and analyse data to investigate the occurrence of health outcomes, their risk factors, and the impact of various interventions or preventive measures.
 
 Epidemiological studies are essential for understanding the health of populations, identifying health disparities, and guiding public health efforts to improve the well-being of communities and societies.
 

04_probability_distributions.ipynb

@@ -1480,7 +1480,7 @@
     "    - What is $\\mathrm{KLD}\\left[\\mathrm{Uniform}(0, 1) \\mid\\mid \\mathrm{Beta}(2, 2)\\right]$?\n",
     "    - What is $\\mathrm{KLD}\\left[\\mathrm{Uniform}(0, 1) \\mid\\mid \\mathrm{Beta}(1, 1)\\right]$?\n",
     "  \n",
-    "4. What is $\\mathrm{KLD}\\left[ \\mathrm{Beta}(5, 2) \\mid\\mid \\mathrm{Uniform}(0, 1)\\right]$. How does it compare to $D_\\mathrm{KL}\\left[\\mathrm{Uniform}(0, 1) \\mid\\mid \\mathrm{Beta}(5, 2)\\right]$ from above?\n",
+    "4. What is $\\mathrm{KLD}\\left[ \\mathrm{Beta}(5, 2) \\mid\\mid \\mathrm{Uniform}(0, 1)\\right]$. How does it compare to $D_\\mathrm{KL}\\left[\\mathrm{Uniform}(0, 1) \\mid\\mid \\mathrm{Beta}(5, 2)\\right]$?\n",
     "`````"
    ]
   },

08_PPLs.md

@@ -55,9 +55,6 @@ From the practical point of view, how can we decide which of the PPLs to choose?
 - <font color='orange'>Functionality</font>: evaluate the language's functionality by examining the availability of a wide range of probability distributions and samplers,
 - <font color='orange'>Oppenness to Customization</font>: consider whether the PPL allows you to define custom probability distributions and samplers,
 - <font color='orange'>Performance</font>: some PPLs may offer optimizations or parallel processing capabilities to improve performance,
-```{margin}
-Speaking of conferences! I am co-organising StanCon 2024 in Oxford. Keep your eyes open for scholarship opportunities. We will use Numpyro in this course, but Stan is an excellent and an incredibly robust option.
-```
 - <font color='orange'>Documentation</font>: the availability of well-documented resources, including official documentation, tutorials, and guides, can significantly impact your learning curve and productivity. A well-documented PPL makes it easier to understand and use its features effectively.
 - <font color='orange'>Community Support</font>: an active and supportive community can be an invaluable resource when you encounter challenges or have questions while working with the PPL. Community forums, discussion groups, and user-contributed content can provide guidance and solutions. Dedicated meetups and conferences.
 - <font color='orange'>Integration</font>: consider whether the PPL can easily integrate with other tools and frameworks you may need for your project. Compatibility with libraries for data manipulation, visualization, or machine learning can streamline your workflow.