People say doing a stuff for 10,000 hours makes you an expert in it. This is my 10,000 hours.

Plan Change

1. Convert existing to tensorflow and proceed in tensorflow and pytorch
2. Do RNN for sent analysis on Imdb only, rest in transformers

Models to Learn:

RNN-GRU-LSTM Sequence-to-sequence Attention Mechanism Transformers Gato

TODO:

Image:
4. YoLo 5. EfficientNet
6. U-Net
7. Nets on COCO Dataset
8. Mask-RCNN
9. ViT

NLP: \

1. Transformers
2. Text Generation / Summarization
3. Machine Translation
4. Handwriting recognition
5. Image Captioning
6. Tinyvoice (Whispernet)
7. Generate Music?

Generation:

1. AE
2. VAE
3. GANs
4. Stable Diffusion

RL:

1. Basic RL
2. Advanced RL
3. Super Advanced RL

Other Topics:

1. Meta Learning
2. ANML
3. RL Data Generation
4. Continual Learning

Completed:

Image: \

1. LeNet - 5
2. AlexNet
3. Residual Learning for Image Recognition
4. Sentiment Analysis - IMDB - LSTM