Most Recent Posts
2024
December 2024
(Day 365) Learning about feature stores - 31 December 2024
(Day 364) Learning about LangSmith and reviewing K8s - 30 December 2024
(Day 363) Data mesh + K8s for MLOps - 29 December 2024
(Day 362) Learning about Apache Pinot + Data Mesh - 28 December 2024
(Day 361) More of Architecting Data and Machine Learning Platforms + Some Flink Forward talks - 27 December 2024
(Day 360) New book - Architecting Data and Machine Learning Platforms + some bootcamp homework - 26 December 2024
(Day 359) Creating a list of books and courses I covered in the last 358 days - 25 December 2024
(Day 358) Ready to learn MLOps from pros - 24 December 2024
(Day 357) MLOps + data drift + starting some summaries for the final blog post - 23 December 2024
(Day 356) Applying analytical patterns - new content from Zach Wilson's bootcamp - 22 December 2024
(Day 355) Continued with the DE with dbt book - 21 December 2024
(Day 354) Reading more about the EU AI act - 20 December 2024
(Day 353) Started reading - The AI Engineer's Guide to Surviving the EU AI Act - 19 December 2024
(Day 352) SCD type 2 exercises + some dbt tests - 18 December 2024
(Day 351) Reading Data Engineering with dbt - 17 December 2024
(Day 350) Using Airflow for a RAG app - 16 December 2024
(Day 349) Finished the Effective ML teams book - 15 December 2024
(Day 348) Apache Flink setup and debugging + starting the book Effective Machine Learning Teams - 14 December 2024
(Day 347) Some ML metrics + Finishing Airflow 101 - 13 December 2024
(Day 346) Some Flink + Airflow 101 - 12 December 2024
(Day 345) Using Apache Iceberg for a WAP exercise - 11 December 2024
(Day 344) Checking out the first chapters from Andriy Burkov's new book - 10 December 2024
(Day 343) First Company Reviewer LLM Report + Dremio Verified Lakehouse Associate - 9 December 2024
(Day 342) Apache Flink 101 + Data Quality - 8 December 2024
(Day 341) Kafka + Streaming - 7 December 2024
(Day 340) Exploring Spark's ML library - 6 December 2024
(Day 339) Going deeper and deeper into DE - 5 December 2024
(Day 338) Going deeper into data lakehouses and Iceberg - 4 December 2024
(Day 337) More about Iceberg and DQ - 3 December 2024
(Day 336) Learning about Write and Read Queries in Apache Iceberg - 2 December 2024
(Day 335) New content from Zach Wilson's free YT bootcamp - 1 December 2024
November 2024
(Day 334) Starting to learn about Apache Iceberg - 30 November 2024
(Day 333) Learning about Data Quality - 29 November 2024
(Day 332) Have to do projects + network - 28 November 2024
(Day 331) More SQL practice before the Jan bootcamp - 27 November 2024
(Day 330) Who are the top 10 NBA players by consecutive 20+ point seasons? - 26 November 2024
(Day 329) Fact Data Modeling homework - 25 November 2024
(Day 328) Week 2 - Fact Data Modeling - 24 November 2024
(Day 327) More of the Designing Data-Intensive Applications book - 23 November 2024
(Day 326) Finally started the Designing Data-Intensive Applications book - 22 November 2024
(Day 325) Dimension modelling - 21 November 2024
(Day 324) I secured a free spot at Zach Wilson's Jan 2025 data engineering bootcamp - 20 November 2024
(Day 323) Predicting subway demand + Additive Dimensions - 19 November 2024
(Day 322) Data Eng camp homework 1 completed (maybe) - 18 November 2024
(Day 321) Slowly changing dimensions - 17 November 2024
(Day 320) Day 1 of Zach Wilson's DE bootcamp - Data Modelling - 16 November 2024
(Day 319) Creating a practical ML notebook to evaluate a model based on some business statistic - 15 November 2024
(Day 318) I'm a scikit-learn professional - 14 November 2024
(Day 317) Streaming + more of Chip Huyen's book - 13 November 2024
(Day 316) Reading more of the infamous Designing ML systems book - 12 November 2024
(Day 315) Finally started reading Chip Huyen's Designing ML systems - 11 November 2024
(Day 314) Streamed + new video + more sklearn docs - 10 November 2024
(Day 313) More of sklearn's 'user guide' - 9 November 2024
(Day 312) Reading more of sklearn's Supervised learning doc - 8 November 2024
(Day 311) Checking out NODES '24, 10th chapter of LLM engineer's handbook, and linear models in sklearn - 7 November 2024
(Day 310) I passed the Scikit-learn Associate Practitioner Certification - 6 November 2024
(Day 309) Finishing scikit-learn's MOOC + AI fairness - 5 November 2024
(Day 308) Streaming for 5 hours (overall) and reviewing sklearn's MOOC - 4 November 2024
(Day 307) Covering sklearn's MOOC on stream - 3 November 2024
(Day 306) Checking out scikit-learn's MOOC - 2 November 2024
(Day 305) More of the LLM Engineer's handbook - 1 November 2024
October 2024
(Day 304) LLMs + some dbt - 31 October 2024
(Day 303) Using my professor's A6000 GPU for LLM fine-tuning - 30 October 2024
(Day 302) Data engineering pipeline from the LLM Engineer's handbook - 29 October 2024
(Day 301) LLM Engineer's Handbook - 28 October 2024
(Day 300) Trying out Neo4j's GraphRAG package - 27 October 2024
(Day 299) ML in PySpark - 26 October 2024
(Day 298) From Pandas to PySpark - 25 October 2024
(Day 297) More about LLMs, and credit risk modelling - 24 October 2024
(Day 296) Neo4j & LLM Fundamentals - 23 October 2024
(Day 295) Starting a Credit Risk Modelling course on Udemy - 22 October 2024
(Day 294) Reading more of sklearn's docs - 21 October 2024
(Day 293) Finishing the book + reading sklearn docs for fun - 20 October 2024
(Day 292) Continuing with the ML for financial risk management book - 19 October 2024
(Day 291) Starting Machine Learning for Financial Risk Management with Python + some math for ML - 18 October 2024
(Day 290) Finishing the book - Financial Data Engineering - 17 October 2024
(Day 289) Reading more of the Fin. DE book + stream - 16 October 2024
(Day 288) New book + scikit-learn's inspection module - 15 October 2024
(Day 287) Calibrating classification models - 14 October 2024
(Day 286) MLE - Model deployment from Andriy Burkov - 13 October 2024
(Day 285) I was muted on stream :( + more LLM fine-tuning - 12 October 2024
(Day 284) PEFT LLMs - Gemma, Mistral, Llama, Qwen - 11 October 2024
(Day 283) Reading more of the MLE book + fine-tuning llama models - 10 October 2024
(Day 282) Chapter 5 from MLE by Andriy Burkov - 9 October 2024
(Day 281) Read chapter 4 of Andriy Burkov's MLE book - 8 October 2024
(Day 280) Reading scikit-learn docs on stream + reading Andryi Burkov's MLE book - 7 October 2024
(Day 279) Neo4j Graph Data Science Certification - SUCCESS! - 6 October 2024
(Day 278) Before Machine Learning Volume 2 - Calculus + Neo4j GDS - 5 October 2024
(Day 277) Neo4j Professional Certificate attempt 1 - 4 October 2024
(Day 276) 4.5hr stream learning about intermediate neo4j queries - 3 October 2024
(Day 275) Finding new books to read + stream - 2 October 2024
(Day 274) Finished the Graph Algorithms for Data Science book + stream - 1 October 2024
September 2024
(Day 273) First stream on youtube and finishing chapter 9 of the graph algs book - 30 September 2024
(Day 272) A bit more of Graph Algorithms for Data Science - 29 September 2024
(Day 271) DE - insight and advice from industry experts - 28 September 2024
(Day 270) DE course by Joe Reis - completed - 27 September 2024
(Day 269) The math behind neural nets + trying the capstone project from DL.AI's DE specialisation - 26 September 2024
(Day 268) Going back to some basics, math, and neo4j - 25 September 2024
(Day 267) Continuing with the DE course by Joe Reis - 24 September 2024
(Day 266) T5 model PEFT - 23 September 2024
(Day 265) Day 6 of the DeepLearning.AI Data Engineering Professional Certificate course - 22 September 2024
(Day 264) Day 5 of the DeepLearning.AI Data Engineering Professional Certificate course - 21 September 2024
(Day 263) Day 4 of the DeepLearning.AI Data Engineering Professional Certificate course - 20 September 2024
(Day 262) Day 3 of the DeepLearning.AI Data Engineering Professional Certificate course - 19 September 2024
(Day 261) Day 2 of the DeepLearning.AI Data Engineering Professional Certificate course - 18 September 2024
(Day 260) DeepLearning.AI Data Engineering Professional Certificate got realeased - 17 September 2024
(Day 259) ML monitoring pipelines + Going deeper into neo4j - 16 September 2024
(Day 258) Math exercises in ML - 15 September 2024
(Day 257) LangChain's intro to LangGraph part 2 - 14 September 2024
(Day 256) Using, finetuning and explaining computer vision to my teammatest - 13 September 2024
(Day 255) The Little Book of Deep Learning - 12 September 2024
(Day 254) Started Intro to LangGraph by LangChain - 11 September 2024
(Day 253) Designing effective ML monitoring with EvidentlyAI Part 2 - 10 September 2024
(Day 252) Designing effective ML monitoring with EvidentlyAI - 9 September 2024
(Day 251) LingoMate and first hackathon completed - 8 September 2024
(Day 250) Seoul Tech Impact Day 1 - 7 September 2024
(Day 249) Seoul Tech Impact hackathon tomorrow - 6 September 2024
(Day 248) New LLM project from my advisor - 5 September 2024
(Day 247) Continuing with AI monitoring using EvidentlyAI - 4 September 2024
(Day 246) First deployment on Kubernetes - 3 September 2024
(Day 245) Streaming dbs + EvidentlyAI course - 2 September 2024
(Day 244) Streaming databases book + advanced RAG techniques - 1 September 2024
August 2024
(Day 243) Finishing a PySpark book - 31 August 2024
(Day 242) PySpark day - 30 August 2024
(Day 241) Techniques for improving RAG pipes - 29 August 2024
(Day 240) Example for transitioning from Docker to K8s - 28 August 2024
(Day 239) 7th place at the KB future finance competition 🥳 - 27 August 2024
(Day 238) Rehearsal for the KB AI competition - 26 August 2024
(Day 237) More unsupervised learning algorithms + submitting the KB project ppt - 25 August 2024
(Day 236) Reading about unsupervised learning algorithms + making the *final* version of our ppt videos - 24 August 2024
(Day 235) Re-recording the real-time pipeline video and getting final feedback on our ppt for the KB project - 23 August 2024
(Day 234) Improving the Grafana dashboard and writing a final script for the KB project presentation - 22 August 2024
(Day 233) Sending notifications for suspicious transactions to customers - 21 August 2024
(Day 232) Creating a script for the technical part of the KB project - 20 August 2024
(Day 231) Advancing to the finals of the 6th Kukmin Bank Future Finance AI competition!!! - 19 August 2024
(Day 230) Watching more educational videos from probabl - 18 August 2024
(Day 229) 'probabl' - a gem of a youtube channel - 17 August 2024
(Day 228) Making a poster for the Not Google Devs Society - 16 August 2024
(Day 227) Reading more about DL at scale - 15 August 2024
(Day 226) Your Personal Finance Assistant - 14 August 2024
(Day 225) Starting the Finance Voice Assistant project - 13 August 2024
(Day 224) Learning about Snowflake and starting the book - Deep Learning at Scale - 12 August 2024
(Day 223) Finishing up Introducing MLOps - 11 August 2024
(Day 222) Fundamentals of Data Engineering and Introducing MLOps in O'Reilly - 10 August 2024
(Day 221) Translating the KB Project info to Korean + New Blog!!! - 9 August 2024
(Day 220) Chapter 2 The Data Engineering Lifecycle - 8 August 2024
(Day 219) Fundamentals of Data Eng and LLM data preprocessing pipelines in Mage - 7 August 2024
(Day 218) ML canvas for the KB fraud transaction detection project - 6 August 2024
(Day 217) KB project meeting and reading bank telemarketing papers - 5 August 2024
(Day 216) Pipelines for XGBoost and CatBoost training, and using the models in the real-time inference pipeline - 4 August 2024
(Day 215) Trying out 'traditional' models on the KB project transaction fraud data - 3 August 2024
(Day 214) The evaluation of my MLOps zoomcamp project arrived - max points - 2 August 2024
(Day 213) Creating a grafana dashboard for the KB project - 1 August 2024
July 2024
(Day 212) Final Glaswegian TTS model - 31 July 2024
(Day 211) 2 hour mark !!! Glaswegian dataset goal - accomplished! + whisper-small fine-tuned - 30 July 2024
(Day 210) 118 minutes of Glaswegian accent audio clips - 29 July 2024
(Day 209) Using Mage for pipeline orchestration in the KB project - 28 July 2024
(Day 208) Setting up docker-services for the KB project, streaming transactions, and the Scottish dataset - 27 July 2024
(Day 207) Finished with neo4j (for now) and thinking about fraud detection models - 26 July 2024
(Day 206) Finishing the Stock Market Analysis zoomcamp (for now) - 25 July 2024
(Day 205) Going back to a basic mlflow service and another meeting for the KB project - 24 July 2024
(Day 204) Transaction data EDA + MLflow & minIO docker setup - 23 July 2024
(Day 203) Starting LLM zoomcamp module 4 - Monitoring - 22 July 2024
(Day 202) Setting up a Graph Convolution Network model to detect fraud credit card transactions - 21 July 2024
(Day 201) Struggling with neo4j and a fraud GNN - 20 July 2024
(Day 200) Kukmin Bank AI competition project idea - 19 July 2024
(Day 199) Continuing with Build an LLM from scratch - 18 July 2024
(Day 198) Transactions Data Streaming Pipeline Porject (v1 completed) - 17 July 2024
(Day 197) Learning about Kafka - 16 July 2024
(Day 196) Learned about 'ML canvas' and more about MLOps - 15 July 2024
(Day 195) Reading about bank term deposit subscription prediction models - 14 July 2024
(Day 194) Using Video Generation Models for Taxi OD Demand Matrix Prediction - 13 July 2024
(Day 193) Chapter 5, 6, and 7 from Effective Data Science Infrastructure - 12 July 2024
(Day 192) Chapter 4 - Scaling with the compute layer (from the book - Effective Data Science Infrastructure) - 11 July 2024
(Day 191) Starting the book - Effective Data Science Infrastructure - 10 July 2024
(Day 190) Learning about evaluating vector search engines for RAG apps - 9 July 2024
(Day 189) I finished the Car Insurance Fraud MLOps project. Thank you MLOps zoomcamp for teaching me so much! - 8 July 2024
(Day 188) Setting up automatically updated monitoring UI using streamlit - 7 July 2024
(Day 187) Setting up postgres, pgAdmin, Grafana and FastAPI to run in Docker - 6 July 2024
(Day 186) Prefect cloud, model serving with FastAPI, and SHAP values - 5 July 2024
(Day 185) Using prefect as my orchestrator for my MLOps project - 4 July 2024
(Day 184) Mlflow experiment tracking and trying out metaflow - 3 July 2024
(Day 183) Failing to install Kubeflow, and setting up mlflow on GCP - 2 July 2024
(Day 182) Learning about feature selection in fraud detection and finding a classifier model with low recall - 1 July 2024
June 2024
(Day 181) Lending club data engineering project - Done - 30 June 2024
(Day 180) From Kaggle to BigQuery dimension tables - an end2end pipeline - 29 June 2024
(Day 179) Using Docker, Makefile, and starting Data modelling for my Lending club project - 28 June 2024
(Day 178) Starting 'Lending club data engineering project' - 27 June 2024
(Day 177) Spark for batch processing - 26 June 2024
(Day 176) Testing, Documentation, Deployment with dbt and visualisations with Looker - 25 June 2024
(Day 175) Learning about and using dbt cloud - 24 June 2024
(Day 174) Starting LLM zoomcamp + Learning about Data Warehouses + BigQuery - 23 June 2024
(Day 173) Terraform, GCP, virtual machines, data pipelines - 22 June 2024
(Day 172) Learning about terraform + adding more data to the Glaswegian audio dataset - 21 June 2024
(Day 171) Data engineering zoomcamp by DataTalksClub - 20 June 2024
(Day 170) Uber data engineering project using GCP and Mage - 19 June 2024
(Day 169) Writing first version of introduction for my paper + day 2 of IEUK - 18 June 2024
(Day 168) First day of Internship Experience UK - Technology by Bright network - 17 June 2024
(Day 167) Learning about model monitoring - 16 June 2024
(Day 166) Buying a new book + pseudocon in Seoul + using Gradio for a quick demo app - 15 June 2024
(Day 165) Starting to use mlflow for my research's model tracking + homework 4 of the MLOps zoomcamp - 14 June 2024
(Day 164) Learning about model deployment (and deleting AWS services) - 13 June 2024
(Day 163) Reading about OD demand matrix prediction models - 12 June 2024
(Day 162) Deploying a mage.ai instance to aws - 11 June 2024
(Day 161) Learning about GANs' use in generating OD demand matrix - 10 June 2024
(Day 160) Simple data engineering pipeline with Prefect, and... MLOps with mage.ai (tons of problems) - 9 June 2024
(Day 159) Learning and using prefect for MLOps orchestration - 8 June 2024
(Day 158) 50 minutes of audio in the Scottish dataset + exploring Mixture Density Networks in GNNs - 7 June 2024
(Day 157) GNN design choices and starting an MLOps book on manning.com - 6 June 2024
(Day 156) Final XCS224W - ML with Graphs homework - 5 June 2024
(Day 155) Reading more about 'historic' (used as baseline) models for spatio-temporal predictions using graphs - 4 June 2024
(Day 154) Diving deeper into Graph Neural Networks used in taxi demand prediction - 3 June 2024
(Day 153) First steps into orchestration and ML pipelines (module 3 from MLOps zoomcamp) - 2 June 2024
(Day 152) SVR & STTCM - Two architectures for taxi demand prediction - 1 June 2024
May 2024
(Day 151) Reading more about taxi OD matrix prediction architectures + more Scottish dataset audio included - 31 May 2024
(Day 150) Learning more about taxi OD matrix prediction + Scottish dataset update - 30 May 2024
(Day 149) Learning about the Origin-Destination Matrix Prediction problem in passenger prediction tasks - 29 May 2024
(Day 148) Microsoft Azure hackathon Day 2 - 28 May 2024
(Day 147) Microsoft Azure hackathon Day 1 - 27 May 2024
(Day 146)] MLOps zoomcamp module 2 homework + some more prep for Microsoft x NVIDIA's hackaton - 26 May 2024
(Day 145) Build & Modernize AI Applications with Azure (prep for Microsoft Azure x NVIDIA hackaton in Seoul) - 25 May 2024
(Day 144) Using Graph Neural Networks to predict taxi passenger demand and origin/destination - 24 May 2024
(Day 143) Forward, backward prop and param update by hand - 23 May 2024
(Day 142) Stanford's XCS224W - ML with Graphs - assignment 4 completed - 22 May 2024
(Day 141) Lognormal random variables and looking for a TA position - 21 May 2024
(Day 140) First 3 chapters of A Primer For The Mathematics Of Financial Engineering by Dan Stefanica - 20 May 2024
(Day 139) MLFlow (MLOps) on AWS - 19 May 2024
(Day 138) Fine-tuning Speech T5 using a very small Glaswegian dataset - 18 May 2024
(Day 137) AWS Summit Seoul Day 2 - 17 May 2024
(Day 136) AWS Summit Seoul Day 1 - 16 May 2024
(Day 135) Going deeper into MLOps - 15 May 2024
(Day 134) Finished CS109 + Scottish dataset project + Started MLOps zoomcamp by DataTalks club - 14 May 2024
(Day 133) Gathering data for the Scottish dataset project + Factor analysis + Grokking ML + MLxFundamentals Day 4 (2) - 13 May 2024
(Day 132) MLx Fundamentals Day 4(1) + CS109 - Fairness in AI - 12 May 2024
(Day 131) Meeting for the Scottish dataset project + CS109 - Deep learning - 11 May 2024
(Day 130) CS109 - MAP, Naive Bayes, Logistic Regression - 10 May 2024
(Day 129) AI with a Scottish accent? + MLE lecture by Chris Piech (Stanford CS109) - 9 May 2024
(Day 128) IBM Consulting Insights Virtual Careers event + More of CS109 - 8 May 2024
(Day 127) Serving an API endpoint for news classification + Stanford's CS109 - 7 May 2024
(Day 126) Optimization lecture by Chi Jin from Princeton University + using Docker for the 1st time - 6 May 2024
(Day 125) MLx Fundamentals Day 2 - Causal representation learning, optimization - 5 May 2024
(Day 124) MLx Fundamentals Day 1 - Intro to ML, Naive Bayes, Factorization methods - 4 May 2024
(Day 123] Optimization algorithms chapter from Dive into DL - 3 May 2024
(Day 122) Dive into Deep Learning - Interactive deep learning book with code, math, and discussions - 2 May 2024
(Day 121) Uncovering the full reason behing multicollinearity + Frequent itemset mining lecture - 1 May 2024
April 2024
(Day 120) Starting Stanford's CS246 - Mining Massive Datasets + MIT's Intro DL - 30 April 2024
(Day 119) Graph Convolutional Transformer application on electronic health records - 29 April 2024
(Day 118) Looking for a new book to read + Oxford ML summer school + short career event - 28 April 2024
(Day 117) Some linear algebra + eigenvector/values and transferring more posts to the new blog - 27 April 2024
(Day 116) Reading some research + transferring posts to the new blog - 26 April 2024
(Day 115) Exploring HuggingFace's capabilities and submitting 3rd homework from the ML with Graphs course - 25 April 2024
(Day 114) Trustworthy Graph AI - 24 April 2024
(Day 113) Making a better blog + Geometric Graph Learning for Biology - 23 April 2024
(Day 112) db2chat - Talk with your (sqlite3) database - 22 April 2024
(Day 111) Advanced Topics in GNNs - 21 April 2024
(Day 110) Learning about Graph Transformers - 20 April 2024
(Day 109) Graph Generative Models - 19 April 2024
(Day 108) Recommender systems + small adjustment to the text2chart webapp - 18 April 2024
(Day 107) Transforming natural language to charts - 17 April 2024
(Day 106) Community structure in networks - 16 April 2024
(Day 105) Network subgraph counting and matching - 15 April 2024
(Day 104) Reasoning over Knowledge Graphs - 14 April 2024
(Day 103) Knowledge Graphs - 13 April 2024
(Day 102) Label propagation in ML with Graphs - 12 April 2024
(Day 101) Doing the Google Cloud Digital Leader Learning Path - 11 April 2024
(Day 100) Embeddings in practice + reading a couple of research papers + trying to deploy an LLM in production - 10 April 2024
(Day 99) XCS224W - ML with Graphs - Theory of GNNs - 9 April 2024
(Day 98) Finishing XCS224W - ML with Graphs' 2nd homework on GNNs Using PyTorch Geometric - 8 April 2024
(Day 97) Review of the GNN structure and training (last 2 days) + starting Colab 2 of XCS224W - ML with Graphs - 7 April 2024
(Day 96) GNN Training Pipeline + looking for opportunities this summer - 6 April 2024
(Day 95) Designing a GNN layer + becoming a fellow of the Royal Statistical Society - 5 April 2024
(Day 94) Link analysis page rank random walks + First assignment + Short intro to GNNs - 4 April 2024
(Day 93) Node embeddings in graphs + some foundational statistics/math - 3 April 2024
(Day 92) Starting the official Stanford XCS224W - ML with Graphs - 2 April 2024
(Day 91) Probability - Multivariate models and Statistics chapters from Probabilistic Machine Learning - 1 April 2024
March 2024
(Day 90) Probability - Univariate Models and colab 0 from XCS224W - ML with Graphs - 31 March 2024
(Day 89) More basics from ISLP - 30 March 2024
(Day 88) Starting the book 'An Introduction to Statistical Learning' - Chapter 2 and 3 - 29 March 2024
(Day 87) Registered for Stanford's XCS224W - Machine Learning with Graphs + RAG webapp with llama-index tutorial - 28 March 2024
(Day 86) Made a youtube video - Chat with your PDF for free in colab using huggingface, mongodb, llama_index, langchain - 27 March 2024
(Day 85) How to write a great research paper - 26 March 2024
(Day 84) Lecture 13 and 14 of CMU 11-711's Advanced NLP - Debugging and model interpretation; Ensembling methods - 25 March 2024
(Day 83) Summary of my PDF RAG from scratch - 24 March 2024
(Day 82) Looking for better parsing methods and prompting techniques for my PDF RAG - 23 March 2024
(Day 81) RAG from scratch - chunking is very important! - 22 March 2024
(Day 80) Starting to write my own RAG from scratch on a bank's T&C pdf - 21 March 2024
(Day 79) Attempting to make a Local Retrieval Augmented Generation (RAG) from Scratch - 20 March 2024
(Day 78) NVIDIA GTC talks + accepted to Stanford AI professional certificate + PERL - 19 March 2024
(Day 77) Review of the ACL 2023 talk, and lecture 10 from CMU's advanced NLP course about retrieval models - 18 March 2024
(Day 76) Finishing the Retrieval-based LM talk, and learning about distillation, quantization and pruning - 17 March 2024
(Day 75) Retrieval-based LMs training and applications - 16 March 2024
(Day 74) Retrieval-based LMs - 15 March 2024
(Day 73) MBR and FUDGE - decoding mechanisms; pre vs post layer normalization - 14 March 2024
(Day 72) Carnegie Mellon University - Advanced NLP Spring 2024 - assignment 1 - 13 March 2024
(Day 71) Backprop, GELU, Tricking ChatGPT, and Stealing part of an LLM - 12 March 2024
(Day 70) Testing my backprop knowledge - 11 March 2024
(Day 69) Training an LLM to generate Harry Potter text - 10 March 2024
(Day 68) Build a LLM from scratch chapter 4 - making the GPT-2 architecture - 9 March 2024
(Day 67) Build a LLM from scratch chapter 3 - self-attention from scratch - 8 March 2024
(Day 66) Starting Build a LLM from scratch by Sebastian Raschka - 7 March 2024
(Day 65) Stanford CS224N (NLP with DL) - Multimodal DL and Model analysis and explanation - 6 March 2024
(Day 64) Stanford CS224N (NLP with DL) - Coreference resolution, Adding knowledge to LMs, Code generation - 5 March 2024
(Day 63) Stanford CS224N (NLP with DL) - Natural Language Generation, Question Answering - 4 March 2024
(Day 62) Stanford CS224N (NLP with DL) - Transformers, Pretraining, RLHF - 3 March 2024
(Day 61) Stanford CS224N (NLP with DL) - Machine translation, seq2seq + a side CDCGAN mini project - 2 March 2024
(Day 60) Stanford CS224N (NLP with DL) - Language modelling, RNNs and LSTMs - 1 March 2024
February 2024
(Day 59) Stanford CS224N (NLP with DL) - Backprop and Dependency Parsing - 29 February 2024
(Day 58) Stanford CS224N (NLP with DL) Lecture 2 - Neural classifiers (diving deeper into word embeddings) - 28 February 2024
(Day 57) Stanford CS224N - Lecture 1. Word vectors - 27 February 2024
(Day 56) I found my next step in the ladder - cs224n NLP with DL by Stanford - 26 February 2024
(Day 55) Learning about tokenization in LLMs - 25 February 2024
(Day 54) I became a backprop ninja! (woohoo) - 24 February 2024
(Day 53) Getting closer to becoming a 'backprop ninja' (thanks to Stanford Uni's cs231n assignments) - 23 February 2024
(Day 52) Learning more about transformers with Andrej Karpathy - 22 February 2024
(Day 51) More of AI503 - High-dim space, random walks and markov chains, VC-dims - 21 February 2024
(Day 50) My ML journey does not end today! - KAIST's AI503 Mathematics for AI (PCA, GMM, SVM) - 20 February 2024
(Day 49) KAIST's AI503 Mathematics for AI (Continuous optimization, When models meet data, Linear regression) - 19 February 2024
(Day 48) KAIST's AI503 Mathematics for AI (Matrix Decompositions) - 18 February 2024
(Day 47) Learning a bit more about GANs and finding more KAIST courses - 17 February 2024
(Day 46) Meeting Transformers again and their implementation - 16 February 2024
(Day 45) Trying to understand VAEs with Professor Choi from KAIST - 15 February 2024
(Day 44) Batch vs Layer vs Group Normalization and GANs (+ found a free KAIST AI course) - 14 February 2024
(Day 43) Coding up LeNet, VGG, InceptionNet, UNet from scratch - 13 February 2024
(Day 42) Creating a UNet with PyTorch - 12 February 2024
(Day 41) A bit advanced computer vision concept review - 11 February 2024
(Day 40) Starting a Self-driving cars course by the University of Toronto - 10 February 2024
(Day 39) Reading papers of powerful CNN models + going back to basics (+ some more Andrej Karpathy lectures) - 9 February 2024
(Day 38) Traffic sign classification and bbox model-PyTorch and more of Andrej Karpathy's talks - 8 February 2024
(Day 37) PyTorch traffic sign classification and detection model - 7 February 2024
(Day 36) Intro to PyTorch - 6 February 2024
(Day 35) TensorFlow Advanced techniques - 5 February 2024
(Day 34) Deploying ML models and TensorBoard - 4 February 2024
(Day 33) Tensorflow deployment specialization and a webapp for recognizing the Korean alphabet - 3 February 2024
(Day 32) Language Transformers and KCSE day 3 - 2 February 2024
(Day 31) Natural Language Processing and KCSE day 2 - 1 February 2024
January 2024
(Day 30) KCSE 2024 day 1 and Face recognition & Neural Style transfer - 31 January 2024
(Day 29) How to do object detection? - 30 January 2024
(Day 28) Diving deeper into Convolutional Neural Networks - 29 January 2024
(Day 27) Improving deep learning models - 28 January 2024
(Day 26) Deep Learning Specialization course by Andrew Ng - 27 January 2024
(Day 25) Using neural nets for time series predictions - 26 January 2024
(Day 24) Using neural nets for time series predictions - 25 January 2024
(Day 23) Tried making an Natural Language Processing model - 24 January 2024
(Day 22) Created a Card image classifier model using Neural networks - 23 January 2024
(Day 21) (Almost) finished prep for TensorFlow developer certificate - 22 January 2024
(Day 20) Natural Language Processing - TensorFlow Developer Certificate Part 3 - 21 January 2024
(Day 19) TensorFlow Developer Certificate Part 2 - Convolutional Neural Networks in TensorFlow - 20 January 2024
(Day 18) Step 1 to TensorFlow Developer Certificate - 19 January 2024
(Day 17) Microsoft's ML-For-Beginners - Classification and Clustering - 18 January 2024
(Day 16) Quiz and practical lab from Andrew Ng's course - 17 January 2024
(Day 15) Quiz and practical lab from Andrew Ng's course - 16 January 2024
(Day 14) Andrew Ng's Machine learning specialization - 15 January 2024
(Day 13) I will be part of Korea Conference on Software Engineering 2024 - 14 January 2024
(Day 12) Neural network model for bank churn prediction and making a webapp for exchange rate pred - 13 January 2024
(Day 11) Joined a 'bank churn prediction' competition on Kaggle - 12 January 2024
(Day 10) Simple linear regression to predict GCPA - 11 January 2024
(Day 9) Simple linear regression to predict GCPA - 10 January 2024
(Day 8) Time series - finding trends - 9 January 2024
(Day 7) Applying the time series knowledge to practice - 8 January 2024
(Day 6) Time series course - Kaggle - 7 January 2024
(Day 5) Kaggle's 'Learn' courses - 6 January 2024
(Day 4) Looking for a ML book and Microsoft's ML-For-Beginners course - 5 January 2024
(Day 3) Intro to time series - 4 January 2024
(Day 2) Finishing the ML course by Calctech - 3 January 2024
(Day 1) Machine learning course by Caltech - 2 January 2024
2023
December 2023
(Pre-study) Some basics before starting my journey - 30 December 2023