Uploaded June 2021 | Updated September 2026, 3 hours ago
You can make this BERT project in 20 minutes. This is a Kaggle NLP challenge where we used Deep Learning for a solution. Bert is a Transformer based model with high performance. Using Huggingface Transformers we are able to load a pretrained BERT model and finetune it quickly and easily. The code for the submission is linked below. This is part of a larger Kaggle series I'm doing, so feel free to check out the first episode that goes over the EDA if you're interested.
Kaggle first episode: youtu.be/HwZkxUNbWgI
Link to notebook: kaggle.com/ejmejm/commonlit-model-v1
You can make this BERT project in 20 minutes. This is a Kaggle NLP challenge where we used Deep Learning for a solution. Bert is a Transformer based model with high performance. Using Huggingface Transformers we are able to load a pretrained BERT model and finetune it quickly and easily. The code for the submission is linked below. This is part of a larger Kaggle series I'm doing, so feel free to check out the first episode that goes over the EDA if you're interested.
Kaggle first episode: youtu.be/HwZkxUNbWgI
Link to notebook: kaggle.com/ejmejm/commonlit-model-v1
![ML Research Idea [Zero to Paper]](https://i.ytimg.com/vi/nSEb6w_BBqE/mqdefault.jpg "ML Research Idea [Zero to Paper]
This episode (part 2) of Zero to Paper covers the idea we will be working on: Text to Goal, or TTG for short. TTG aims to translate natural language into a reward function for a Reinforcement Learning problem. This research project aims to leverage recent advancements in NLP and Computer Vision to make reward functions easier and more natural to craft.
I also briefly touch on how I come up with ideas an what is important to me. I hope this will be helpful to anyone wonder how to do ML research!
Zero to Paper playlist: https://www.youtube.com/watch?v=74fKCvr5n5o&list=PL_49VD9KwQ_ONxENRk11jFEI3_pqAwaug
RL Theory series if you want to get into RL: https://www.youtube.com/watch?v=1OI0uuz9jkI&list=PL_49VD9KwQ_OML1Knh-Yb7FUFkhTLS0jL")
