eagle0504/AI-Decoded
1
1import streamlit as st2 3st.set_page_config(page_title="Hello", page_icon="👋", layout="wide")4 5st.write("# Welcome to AI Decoded! 👋")6 7st.sidebar.success("Select a demo above.")8 9st.markdown(10 """11 Streamlit is an open-source app framework built specifically for12 Machine Learning and Data Science projects.13 14 - Click on `Files`, and then go to `docs/notebooks` for access of python notebooks15 - For more information, go [here](https://wyn-education.streamlit.app/)16 17 ## Table of Content18 19 | Index | Title | Description |20 |-------|-------------------------------------------------------------------------------------------|---------------------------------------------------------------|21 | 0 | intro to python - creating pi | Learning Python by simulating pi |22 | 0 | intro to python | Learning Python basics |23 | 01 | numpy, pandas, matplotlib | Introduction to essential Python libraries for data science |24 | 02 | ann and cnn | Exploring artificial neural networks and convolutional neural networks |25 | 02 | gradient descent in neural networks | Understanding gradient descent optimization in neural networks|26 | 02 | run a neural network models on tpu | Running neural network models on Tensor Processing Units (TPU)|27 | 03 | run an installed neuralnet | Executing a pre-installed neural network model |28 | 04a | more in cnn (famous cnn) | Deep dive into famous convolutional neural network architectures |29 | 04a | more in cnn | Further exploration of convolutional neural networks |30 | 04a | popular cnn walkthrough with training and evaluating on test set | Step-by-step guide to training and evaluating CNNs on a test dataset |31 | 04b | 3d cnn using captcha ocr | Using 3D CNNs for optical character recognition in CAPTCHAs |32 | 04b | vit classifier on mnist | Implementing a Vision Transformer (ViT) classifier on MNIST dataset |33 | 04c | chestxray classification | Classifying chest X-ray images using neural networks |34 | 04d | class activation map | Visualizing regions affecting neural network decisions with class activation maps |35 | 05 | fine tuning neural network | Techniques for fine-tuning pre-trained neural networks |36 | 06a | autoencoder | Exploring autoencoders for unsupervised learning |37 | 06b | image denoising | Using neural networks to remove noise from images |38 | 07a | variational autoencoder | Learning about variational autoencoders and their applications |39 | 07b | neural network regressor + bayesian last layer | Building a neural network regressor with a Bayesian approach |40 | 08 | inference of autoencoder | Performing inference with autoencoders |41 | 09a | image segmentation | Techniques for segmenting images using neural networks |42 | 09b | image segmentation unet | Implementing U-Net architecture for image segmentation |43 | 09c | image segmentation unet dense style | Advanced U-Net with dense layers for image segmentation |44 | 09d | image segmentation unet attention style | U-Net with attention mechanisms for improved segmentation |45 | 10 | dcgan on masked mnist | Using DCGANs on MNIST dataset with masked inputs |46 | 10 | masked image model | Exploring models for processing images with masked areas |47 | 10 | reconstruct mnist fashion image from ae to vapaad | Reconstructing fashion images from autoencoders to VAPAAD models |48 | 10 | reconstruct mnist image from ae to vapaad | Image reconstruction from autoencoders to VAPAAD models |49 | 10 | vapad test v1 | Initial tests on VAPAAD model performance |50 | 10 | vapad test v2 | Further testing on VAPAAD model enhancements |51 | 10a | dcgan | Exploring Deep Convolutional Generative Adversarial Networks |52 | 10b | dcgan on masked mnist | Applying DCGANs to MNIST with masked inputs |53 | 11a | huggingface on names | Utilizing Hugging Face libraries for name-based tasks |54 | 11b | transformers | Comprehensive guide to using transformer models |55 | 11c | lstm on IMDB | Applying LSTM networks for sentiment analysis on IMDB reviews |56 | 11c | simple RNN on sine function | Exploring simple recurrent neural networks with sine functions |57 | 11d | text encoder using transformers | Building a text encoder with transformer architecture |58 | 11e | attention layer sample | Examples and applications of attention layers |59 | 11f | convolutional lstm next frame prediction | Using convolutional LSTMs for predicting video frames |60 | 11g | convolutional lstm next frame prediction | Further exploration of convolutional LSTMs for frame prediction|61 | 11h | next frame prediction convolutional lstm | Advanced techniques in LSTM-based video frame prediction |62 | 11i | next frame prediction convolutional lstm + attention | Integrating attention with LSTMs for enhanced frame prediction |63 | 11j | next frame prediction vapaad | Predicting video frames using VAPAAD models |64 | 11k | next frame ecoli prediction instruct-vapaad class (updated) with stop gradient | Updated E. coli frame prediction with VAPAAD and stop gradients|65 | 11k | next frame prediction instruct-vapaad class (updated) with stop gradient | Improved frame prediction with updated VAPAAD and stop gradients |66 | 11k | next frame prediction instruct-vapaad class with stop gradient | Frame prediction using VAPAAD with gradient stopping |67 | 11k | next frame prediction instruct-vapaad with stop gradient | Enhancing VAPAAD models with stop gradient techniques |68 | 11k | next frame prediction instruct-vapaad | Introduction to frame prediction with VAPAAD models |69 | 13 | bert on IMDB | Applying BERT for sentiment analysis on IMDB reviews |70 | 14 | music generation | Exploring neural networks for generating music |71 | 15 | functional api and siamise network | Utilizing Keras Functional API for Siamese networks |72 | 16a | use lstm to forecast stock price | Forecasting stock prices with LSTM networks |73 | 16b | use neuralprophet to forecast stock price | Stock price prediction using the NeuralProphet model |74 | 16c | use finviz to get basic stock data | Retrieving stock data using the Finviz platform |75 | 16d | dynamic time warping | Exploring dynamic time warping for time series analysis |76 | 17 | introduction to modeling gcl | Basics of modeling with Generative Causal Language (GCL) |77 | 18a | image classification with vit | Using Vision Transformers for image classification |78 | 18b | transformer | Deep dive into the workings of transformer models |79 | 18c | transformers can do anything | Exploring the versatility of transformer models |80 | 18d | attention | Understanding the mechanisms and applications of attention |81 | 18e | transformers and multi-head attention | Advanced topics on transformers and multi-head attention |82 | 19a | text generation with GPT | Generating text using GPT models |83 | 19b | quick usage of chatGPT | Guide to quickly deploying chatGPT for conversational AI |84 | 19c | build quick chatbot using clinical trails data | Creating a chatbot with clinical trials data for rapid response|85 | 19c | fine tune chatgpt clinical trials data - part 1 | Part 1 of fine-tuning chatGPT with clinical trials data |86 | 19c | fine tune chatgpt clinical trials data - part 2 | Part 2 of fine-tuning chatGPT with clinical trials data |87 | 19c | fine tune chatgpt olympics data - part 1 | Part 1 of fine-tuning chatGPT with data from the Olympics |88 | 19d | distances between two sentences | Computing semantic distances between sentences |89 | 20b | generate ai photo by leapai | Generating photos using LeapAI technology |90 | 21 | neural machine learning translation | Exploring neural machine translation systems |91 | 21a | image classification with vision transformer | Classifying images using Vision Transformers |92 | 21b | image segmentation | Techniques for segmenting images with neural networks |93 | 21b | image_classification_with_vision_transformer_brain_tumor | Classifying brain tumor images with Vision Transformers |94 | 21b | object detection using vision transformer | Object detection using Vision Transformers |95 | 21b | shiftvit on cifar10 | Applying ShiftViT architecture to CIFAR-10 dataset |96 | 21c | face recognition | Implementing facial recognition systems |97 | 21d | neural style transfer | Exploring neural style transfer techniques |98 | 21e | 3d image classification | Classifying 3D images using neural networks |99 | 21f | object detection inference from huggingface | Performing object detection inference using Hugging Face models|100 | 21f | object detection inference | Techniques for conducting object detection inference |101 | 22a | monte carlo policy gradient | Implementing Monte Carlo policy gradients for reinforcement learning |102 | 22b | dql carpole | Applying deep Q-learning to the CartPole problem |103 | 22c | dqn carpole keras | Implementing a deep Q-network for CartPole with Keras |104 | 23a | actor-critic intro using toy data | Introduction to actor-critic methods with toy data |105 | 23a | actor-critic intro | Basics of actor-critic reinforcement learning methods |106 | 23b | actor-critic with ppo | Implementing actor-critic with Proximal Policy Optimization |107 | 24a | basic langchain tutorial | Introductory tutorial on using LangChain |108 | 24a | fine tune falcon on qlora | Fine-tuning Falcon models on Qlora dataset |109 | 24a | fine tune llm bert using hugginface transformer | Fine-tuning BERT models using Hugging Face transformers |110 | 24a | semantic_similarity_with_bert | Exploring semantic similarity using BERT models |111 | 24b | character level text generation using lstm | Generating text at the character level with LSTM networks |112 | 24b | custom agent with plugin retrieval using langchain | Creating custom agents with plugin retrieval in LangChain |113 | 24b | fast bert embedding | Generating quick embeddings using BERT |114 | 24b | internet search by key words | Conducting internet searches based on key words |115 | 24b | palm api getting started | Getting started with PALM API |116 | 24b | pandasAI demo | Demonstrating capabilities of pandasAI library |117 | 24b | scrape any PDF for QA pairs | Extracting QA pairs from PDF documents |118 | 24b | scrape internet with public URL | Scraping the internet using public URLs |119 | 24b | self refinement prompt engineering | Developing refined prompts for better AI responses |120 | 24b | semantic similarity with keras nlp | Exploring semantic similarity using Keras NLP tools |121 | 24b | serpapi openai | Utilizing SerpAPI with OpenAI services |122 | 24c | fine tune customized qa model | Fine-tuning a customized QA model |123 | 24d | fine tune llm tf-f5 | Fine-tuning LLM TF-F5 for specialized tasks |124 | 24d | langchain integrations of vector stores | Integrating LangChain with vector storage solutions |125 | 24d | performance evaluation of finetuned model, chatgpt, langchain, and rag | Evaluating performance of various finetuned models and systems |126 | 24e | working with langchain agents | Guide to using LangChain agents |127 | 24f | api call to aws lambda with llama2 deployed | Making API calls to AWS Lambda with Llama2 deployed |128 | 24f | fine tune bert using mrpc dataset and push to huggingface hub | Fine-tuning BERT on MRPC dataset and publishing to Hugging Face|129 | 24f | fine tune Llama 2 using ysa data in colab | Fine-tuning Llama 2 with YSA data on Colab |130 | 24f | fine tune llama2 in colab | Fine-tuning Llama2 on Google Colab |131 | 24f | fine tune llama2 using guanaco in colab | Fine-tuning Llama2 using Guanaco dataset on Colab |132 | 24f | fine tune llama3 with orpo | Fine-tuning Llama3 with ORPO dataset |133 | 24f | fine tune Mistral_7B_v0_1 using dataset openassistant guanaco | Fine-tuning Mistral_7B_v0_1 with OpenAssistant Guanaco dataset |134 | 24f | hqq 1bit | Exploring 1bit quantization for model compression |135 | 24f | inference endpoint interaction from huggingface | Managing inference endpoints from Hugging Face |136 | 24f | inference from llama-2-7b-miniguanaco | Inference with the Llama-2-7B-MiniGuanaco model |137 | 24f | jax gemma on colab tpu | Utilizing JAX Gemma on Google Colab TPUs |138 | 24f | llm classifier tutorials | Tutorials on using large language models for classification |139 | 24f | load and save models from transformers package locally | Techniques for loading and saving Transformer models locally |140 | 24f | load sciq formatted dataset from huggingface into chroma | Loading SciQ formatted datasets from Hugging Face into Chroma |141 | 24f | load ysa formatted dataset from huggingface into chroma | Loading YSA formatted datasets from Hugging Face into Chroma |142 | 24f | ludwig efficient fine tune Llama2 7b | Efficiently fine-tuning Llama2 7B using Ludwig |143 | 24f | process any custom data from pdf to create qa pairs for rag system and push to huggingface | Processing custom PDF data to create QA pairs for RAG system |144 | 24f | process custom data from pdf and push to huggingface to prep for fine tune task of llama 2 using lora | Preparing custom PDF data for Llama 2 fine-tuning using Lora |145 | 24f | prompt tuning using peft | Using prompt engineering and tuning for fine-tuning models |146 | 24f | started with llama 65b | Getting started with the Llama 65B model |147 | 24f | what to do when rag system hallucinates | Handling hallucinations in RAG systems |148 | 24g | check performance boost from QA context pipeline | Evaluating performance improvements from QA context pipelines |149 | 24h | text generation gpt | Exploring text generation capabilities of GPT models |150 | 24i | google gemini rest api | Using Google Gemini REST API |151 | 26 | aws textract api call via post method | Making POST method API calls to AWS Textract |152 | 27a | image captioning vit-gpt2 on coco2014 data | Captioning images with VIT-GPT2 on COCO2014 dataset |153 | 27b | image captioning cnn+transformer using flickr8 (from fine-tune to HF) | Image captioning using CNN and transformers on Flickr8 dataset |154 | 27b | image captioning cnn+transformer using flickr8 data save and load locally | Saving and loading CNN+transformer models for image captioning |155 | 27c | keras integration with huggingface tutorial | Integrating Keras with Hugging Face libraries |156 | 27d | stock chart captioning (from data cleanup to push to HF) | Developing stock chart captioning models from start to finish |157 | 27d | stock chart image classification using vit part 1+2 | Classifying stock charts using VIT in two parts |158 | 27d | stock chart image classifier using vit | Classifying stock charts using Vision Transformers |159 | 27e | keras greedy image captioning (inference) | Performing inference with Keras models for image captioning |160 | 27e | keras greedy image captioning (training) | Training Keras models for greedy image captioning |161 | 28a | quantized influence versus cosine similarity | Comparing quantized influence and cosine similarity measures |162 | 28b | quantized influence versus cosine similarity | Deep dive into quantized influence metrics versus cosine similarity |163 | 28c | quantized influence versus cosine similarity | Analyzing the impact of quantized influence in machine learning models |164 | 29a | dna generation to protein folding | From generating DNA sequences to modeling protein folding |165 | 30a | v-jepa (ish) on mnist data | Applying V-JEPA models on MNIST dataset |166 | 30a | vapad test v1 | Initial tests and evaluation of VAPAAD models |167 | 30a | vapad test v2 | Further evaluations and improvements of VAPAAD models |168 | 30e | moving stock returns instruct-vapaad class (success) | Successful implementation of moving stock returns with VAPAAD |169 | 30e | redo rag from scratch using openai embed and qim | Rebuilding RAG systems using OpenAI Embeddings and QIM |170 | 31a | redo rag from scratch using openai embed and qim | Reconstructing RAG systems from the ground up with new technologies |171 | 31b | redo rag from scratch using openai embed + qim + llama3 | Advanced rebuilding of RAG using Llama3, OpenAI Embed, and QIM |172 | 31c | redo rag with auto question generation | Enhancing RAG systems with automatic question generation |173 | 32a | text-to-video initial attempt | Initial trials in converting text descriptions to video content|174 | _ | audio processing in python | Techniques for processing audio data in Python |175 | _ | blockchain tutorial (long) | Comprehensive guide to blockchain technology |176 | _ | blockchain tutorial | Introduction to blockchain concepts and applications |177 | _ | dataframe querying using pandasAI | Using pandasAI for advanced dataframe querying |178 | _ | extract nii files | Techniques for extracting data from NII file formats |179 | _ | fake patient bloodtest generator | Generating synthetic patient blood test data for simulations |180 | _ | Image Processing in Python_Final | Comprehensive guide to image processing in Python |181 | _ | kmeans_from_scratch | Implementing K-means clustering algorithm from scratch |182 | _ | Manifold learning | Exploring manifold learning techniques for dimensionality reduction |183 | _ | openai new api | Guide to using the latest OpenAI API features |184 | _ | pca | Principal component analysis for data simplification |185 | _ | rocauc | Understanding ROC-AUC curves and their applications |186 | _ | simulate grading rubrics with and without max function | Simulating grading systems with variations in calculation |187 | _ | simulation of solar eclipse | Modeling solar eclipse events |188 | _ | Unrar, Unzip, Untar Rar, Zip, Tar in GDrive | Techniques for managing compressed files in Google Drive |189 190 191"""192)193