forked from mmistakes/minimal-mistakes
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
8a67ce8
commit b556f3e
Showing
13 changed files
with
192 additions
and
49 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,60 @@ | ||
--- | ||
title: "About" | ||
permalink: /about | ||
layout: single | ||
author_profile: true | ||
--- | ||
<script | ||
src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML" | ||
type="text/javascript"> | ||
</script> | ||
|
||
# Intro | ||
Hello, I am a Machine Learning Engineer with a background in Physics and Chemistry. | ||
I am very interested in applications of ML to science, particularly to the problem of climate | ||
change. | ||
I am currently working as a Machine Learning Engineer at [Carbon Re]("https://carbonre.com/"), | ||
a startup that uses machine learning to help heavy industry companies reduce their carbon footprint. <br> | ||
<br> | ||
Most of my interests revolve around the intersection of ML and the physical sciences. | ||
Right now I am particularly interested in: | ||
applications of deep learning to PDEs (PINNs, NeuralODEs...), | ||
Reinforcement Learning for dynamical systems and Bayesian Deep Learning | ||
|
||
# My favourite derivations | ||
## The MAP estimate of a linear model | ||
|
||
$$ | ||
\begin{align*} | ||
\theta_{\text{MAP}} &= \arg\max_{\theta} p(\theta | \mathcal{D})\\ | ||
&= \arg\max_{\theta} \frac{p(\mathcal{D} | \theta) p(\theta)}{p(\mathcal{D})} \\ | ||
&= \arg\max_{\theta} p(\mathcal{D} | \theta) p(\theta) \\ | ||
&= \arg\max_{\theta} \log p(\mathcal{D} | \theta) + \log p(\theta) \\ | ||
&= \arg\max_{\theta} \log \prod_{i=1}^N p(y_i | x_i, \theta) + \log p(\theta) \\ | ||
&= \arg\max_{\theta} \sum_{i=1}^N \log p(y_i | x_i, \theta) + \log p(\theta) \\ | ||
&= \arg\max_{\theta} \sum_{i=1}^N \log \mathcal{N}(y_i | \theta^T x_i, \sigma^2) + \log \mathcal{N}(\theta | 0, \alpha^2) \\ | ||
&= \arg\max_{\theta} \sum_{i=1}^N -\frac{1}{2\sigma^2} (y_i - \theta^T x_i)^2 - \frac{1}{2\alpha^2} \theta^T \theta \\ | ||
&= \arg\min_{\theta} \sum_{i=1}^N (y_i - \theta^T x_i)^2 + \frac{\sigma^2}{\alpha^2} \theta^T \theta \\ | ||
&= \arg\min_{\theta} \sum_{i=1}^N (y_i - \theta^T x_i)^2 + \lambda \theta^T \theta \\ | ||
\end{align*} | ||
$$ | ||
Which is the well-known Ridge regression problem. | ||
## The Particle in a box | ||
The time-independent Schrödinger equation for a particle in a box is given by: | ||
|
||
$$ | ||
\begin{align*} | ||
-\frac{\hbar^2}{2m} \frac{d^2 \psi(x)}{dx^2} + V(x) \psi(x) &= E \psi(x) \\ | ||
-\frac{\hbar^2}{2m} \frac{d^2 \psi(x)}{dx^2} &= (E - V(x)) \psi(x) \\ | ||
\end{align*} | ||
$$ | ||
|
||
Where $$V(x) = 0$$ for $$0 < x < L$$ and $$V(x) = \infty$$ otherwise. | ||
Solving the equation by inspection we can see that : | ||
|
||
$$ | ||
\begin{align*} | ||
\psi(x) &= A \sin(kx) + B \cos(kx) \\ | ||
k &= \frac{\sqrt{2mE}}{\hbar} | ||
\end{align*} | ||
$$ |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,8 @@ | ||
--- | ||
title: "Blogs" | ||
permalink: /blogs | ||
layout: single | ||
author_profile: true | ||
--- | ||
|
||
hello world |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,33 @@ | ||
--- | ||
title: "Invited Talks" | ||
permalink: /invited-talks | ||
layout: single | ||
author_profile: true | ||
--- | ||
|
||
<details> | ||
<summary><i>London 2050</i>, UCL Engineering 2024</summary> | ||
<br> | ||
Invited for a panel with BNP Paribas and ABB to talk about the future of London. | ||
</details> | ||
<br> | ||
|
||
<details> | ||
<summary><i>Machine Learning Engineer at a Climate Tech Startup</i>, UCL Statistics Society, 2023</summary> | ||
<br> | ||
I spoke about my experience as a Machine Learning Engineer at Carbon Re, a climate tech startup. I talked about the challenges of working in a startup as well as the experience of shifting from academia to industry. | ||
</details> | ||
<br> | ||
|
||
<details> | ||
<summary><i>Tips on running a succesful Masters Project</i>, UCL AI for Sustainable Development cohort 2022</summary> | ||
<br> | ||
My Masters project was a huge success and I was invited to give a talk to the incoming students on how to run a successful project by my supervisor Maria Perez Ortiz who is the head of the course. I talked about the importance of a preparing correctly. Especially, given that I had created my own topic. | ||
</details> | ||
<br> | ||
|
||
<details> | ||
<summary><i>What's the big deal with the James Webb Space Telescope?</i>, UCL AI Centre, 2022</summary> | ||
<br> | ||
I was invited to give a talk at the UCL AI Centre on the James Webb Space Telescope. I talked about the scientific goals of the mission and its potential impact for the big topics in astrophysics and cosmology such as the Hubble tension and galaxy seeding. | ||
</details> |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,38 @@ | ||
--- | ||
title: "Publications" | ||
permalink: /publications | ||
layout: single | ||
author_profile: true | ||
--- | ||
<details> | ||
|
||
<summary> <a href="https://arxiv.org/abs/2312.06527" target=_blank >[1]</a> <i>Can Reinforcement Learning support policy makers? A preliminary study with Integrated Assessment Models</i>, <br> NeurIPS 2023 Workshop on Tackling Climate Change with AI </summary> | ||
<br> | ||
As part of my Masters at UCL, I worked on using Reinforcement Learning in an Integrated | ||
Assessment model. This was very novel work and there was very little prior work to base my work on. | ||
<br><br> | ||
It was a hugely challenging project, but I learned a lot about RL and the problems in applying it to dynamical systems. | ||
Notably, I wrote my own implementations of A2C, PPO, DQN, Double DQN (with duelling nets + PER buffer) in Pytorch. | ||
I subsequently published my work at the workshop "Tackling Climate Change with AI" at NeurIPS 2023. | ||
<br><br> | ||
|
||
You can find my NeurIPS publication <a href="https://arxiv.org/abs/2312.06527" target=_blank >here</a> and my poster <a href="/assets/images/neuripsposterfinal.png" target=_blank >here</a>. | ||
</details> | ||
<br> | ||
|
||
|
||
|
||
<br> | ||
<br> | ||
<br> | ||
<br> | ||
<br> | ||
<br> | ||
<br> | ||
<br> | ||
<br> | ||
<br> | ||
<br> | ||
|
||
|
||
Looking a bit empty here... Help me fill this up :) |
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.