-
Finetune an LLM to play the game of '20 questions'
...and won rank 13/832 in a Kaggle simulation competition.
-
How to finetune an LLM to classify responses from other LLMs
...and won a SECOND PLACE in the 'H2O.ai Predict the LLM', met with H2O.ai CEO, and recruited by them!
-
Santa again gave me another GOLD medal!
Another Christmas, another traditional Santa contest, another constraint optimization problem, another gold medal (rank 9/874)!
-
I finally WIN a Kaggle competition, rank 1/2605 !!!
I finished 1/2600 teams in the Google Brain Ventilator Pressure Prediction!
-
Imitation learning by U-Net for a multi-player strategic game
I will show how a data-driven approach (semantic segmentation) can mimic rule-based top bots in the Kaggle 4-Agent Halite IV Competition, and secured rank 8/1140!
-
Hidden Markov model (alone!) can almost win me a Kaggle competition
...instead I finished 3rd due to an unfortunate data leak that 2 other teams exploited in the Liverpool Ion Switching Competition
-
Ensemble zoo never disappoints!
... but must be equipped with counter-overfitting measures to win a Kaggle Gold medal!
-
CPLEX vs Gurobi
A good experience using Gurobi with custom handles to win rank 17/1620 in Kaggle Santa 2019!
-
The elegance of Policy Gradient in reinforcement learning (part 1)
I will the 'magic' of PG of RL in a magical way.
-
Graph neural networks shine in quantum chemistry modeling
How I won a gold medal rank 10/2749 in the Kaggle Predicting Molecular Properties challenge!
-
Write 3000 lines of python code to solve a strange traveling salesman problem
How a weird TSP problem forced us to write custom algorithms and finally seized rank 8/1874 in Kaggle Santa 2018! (plus an introduction to Kotlin!)
-
The power of DBSCAN -- an unsupervised clustering algorithm
How I surprisingly won my 1st Kaggle GOLD medal (10/656) with DBSCAN in a challenging Quantum Physics particle tracking problem