DL_HW

Various Deep Learning Projects (2022- 2023)

This repo demonstrates multiple Deep Learning Techniques including:

1. introduction to Deep learning: Solving digit recognition problem by building a from scratch neural network and loss function.
2. Deep dive into neural network structures, loss functions, backpropagation, and Training loops.
3. Building self-made neural network for Computer vision tasks, solving image recognition problem on CIFAR dataset.
4. Using pretrained model on ImageNet dataset for image classification and Dogs Vs Cats dataset.
5. Perform Natural Language Processing using Encoder-Decoder structure to estimate the salary based on the job title.
6. Introducing CBOW and Word2vec neural networks to solve embeddings tasks.
7. Deep dive into Transformers pre-trained models.
8. Deep models interpretability using SHapley and smooth grad
9. Large Language Models and Their Implications, Prompt engineering, LLM fine-tuning.
10. Introduction to Denoising Autoencoders and Image retrieval problem.
11. Development of GAN (Generative Adversarial Networks) for human faces generation tasks.
12. Speech processing pipeline using Deep learning.

Skills developed: pandas | pytorch | tensorflow | numpy | GANs | encoder-decoder | model-finetuning | LLM | Prompt engineering | models interpretability | SHapley | Transformers | HuggingFace | genism | nltk | python.

This repo is part of the DL course, HSE, Moscow, Russia.