Tan Pengshi Alvin – Medium

Tan Pengshi Alvin

Pinned

Tan Pengshi Alvin
in
Towards AI

Transfer Learning and Convolutional Neural Networks (CNN) — Complete Guide

A complete guide from CNN to Transfer Learning, with application on Kaggle’s Cat versus Dog dataset

22 min readSep 11, 2022

--

1

Transfer Learning and Convolutional Neural Networks (CNN) — Complete Guide

--

1

Pinned

Tan Pengshi Alvin
in
Towards Data Science

The Complete Guide to Effective Learning in Artificial Intelligence

A fundamental and complete guide to skyrocket your growth in Artificial Intelligence (or really in any subject)

26 min readOct 31, 2021

--

The Complete Guide to Effective Learning in Artificial Intelligence

--

Tan Pengshi Alvin
in
Towards AI

Graph Neural Networks (GNN) — Concepts and Applications

Exploring the concept and applications of Graphs, and how to apply Neural Networks to it

20 min readMay 23, 2024

--

Graph Neural Networks (GNN) — Concepts and Applications

--

Tan Pengshi Alvin
in
Towards AI

Demystifying the Receiver Operating Characteristic (ROC) Curve

Interpreting the metrics behind a supervised classification model, in particular, the ROC curve and AUC

8 min readApr 22, 2024

--

3

Demystifying the Receiver Operating Characteristic (ROC) Curve

--

3

Tan Pengshi Alvin
in
Towards AI

Reinforcement Learning: Multi-Agent Cooperation with MADQN— Part 5

Multi-agent reinforcement learning with 3 MADQN frameworks on the ma-gym’s “Switch4” environment

13 min readDec 24, 2023

--

Reinforcement Learning: Multi-Agent Cooperation with MADQN— Part 5

--

Tan Pengshi Alvin
in
ILLUMINATION

Proposing the Singapore River as UNESCO World Heritage Site

Consideration of factors and background in qualification for UNESCO World Heritage status

7 min readOct 19, 2023

--

Proposing the Singapore River as UNESCO World Heritage Site

--

Tan Pengshi Alvin
in
Towards AI

Reinforcement Learning: Function Approximation and Deep Q-Networks — Part 4

Reinforcement Learning with continuous state spaces and gradient descent techniques

14 min readOct 2, 2023

--

Reinforcement Learning: Function Approximation and Deep Q-Networks — Part 4

--

Tan Pengshi Alvin
in
Towards AI

Reinforcement Learning: SARSA and Q-Learning — Part 3

Introducing the Temporal Difference family of iterative techniques to solve the Markov Decision Process

9 min readSep 6, 2023

--

Reinforcement Learning: SARSA and Q-Learning — Part 3

--

Tan Pengshi Alvin
in
Towards AI

Reinforcement Learning: Dynamic Programming and Monte Carlo — Part 2

Introducing two simple iterative techniques to solve the Markov Decision Process

12 min readSep 1, 2023

--

Reinforcement Learning: Dynamic Programming and Monte Carlo — Part 2

--

Tan Pengshi Alvin
in
Towards AI

Reinforcement Learning: Markov Decision Process — Part 1

Introducing the backbone of Reinforcement Learning — The Markov Decision Process

12 min readAug 29, 2023

--

2

Reinforcement Learning: Markov Decision Process — Part 1

--

2

Tan Pengshi Alvin

Tan Pengshi Alvin

Data Scientist, AI and Software Engineer 🇸🇬. Shares simple codes, technical Data Science concepts and ideas. LinkedIn: https://www.linkedin.com/in/tanpengshi/

Following

Help
Status
About
Careers
Press
Blog
Privacy
Terms
Text to speech
Teams