100DaysOfMLCode
#100DaysofMLCode Challenge
Ask AI about 100DaysOfMLCode
Powered by Claude · Grounded in docs
I know everything about 100DaysOfMLCode. Ask me about installation, configuration, usage, or troubleshooting.
0/500
Reviews
Documentation
DAY 1: Today I've learned about Data Preprocessing:
- Importing the libraries
- Importing the dataset
- Taking care of missing data
- Encoding categorical data
- Splitting the dataset into the Training set and Test set
- Feature Scaling
Source: Machine Learning A-Z™: Hands-On Python & R In Data Science Code
LinkedIn Post
DAY 2:
Today I've learned and implemented Simple Linear Regression.
Code
LindedIn Post
DAY 3:
Started reading a book called "Naked Statistics: Stripping the Dread from the Data" by Charles Wheelan.
Today I've learned about
- Multiple Linear Regression. Code
- Backward Elimination
- Forward Selection
- Bidirectional Elimination
LinkedIn Post
DAY 4:
Today I've learned and implemented Polynomial Regression.
Code
LinkedIn Post
DAY 5:
Today I've learned and implemented SVR model.
Code
LinkedIn Post
DAY 6: Today I've learned and implemented:
DAY 7: Today I've learned and implemented Logistic Regression. Code
DAY 8: Today I've learned and implemented:
DAY 9: Today I've learned and implemented:
DAY 10: Today I've learned about False Positives & False Negatives, Confusion Matrix, Accuracy Paradox, CAP Curve.
DAY 11: Today I've learned and implemented K-Means Clustering. Code
DAY 12: Today I've learned and implemented Hierarchical Clustering. Code
DAY 13-20:
I've completed the Machine Learning A-Z course on Udemy. I've also completed reading the book "Naked Statistics" by Charles Wheelan.
LinkedIn Post
DAY 21-25: I’ve learned and practiced Numpy, Pandas, and Tensorflow. I’ve also done some basic ML projects like text classification (Fashion MNIST) and text classification (IMDB reviews) based on some youtube tutorials.
DAY 26: Resuming after a break. Revised ML course by Andrew NG on coursera. Completed two weeks' content and assignments. Working on optional assignments. Course Link
DAY 27, 28: Completed the optional assignments on Multivariate Cost function, Gradient Descent and Normal equation. Learned and implemented vectorization of cost function and gradient descent for easy coding in octave.
DAY 29: Revised concepts of Deep learning. Understood the concept with an example of Demand Prediction of a product.
DAY 30: Reviced concepts of Gradient Descent and Back Propagation.
DAY 30: Learned how to implement forward propagation in neural networks using numpy.
DAY 31: Implemented forward propagation using tensorflow and numpy
DAY 32: Introduction to Multi class regression and softmax function.
DAY 33: Got a better and deeper understanding of how Back Propagation works and why it's very important in neural networks.
DAY 34: Started with GenAI with LLMs course on Coursera. Revised the working of transformer.
DAY 35: Learned about bias and variance in ML models.
DAY 36: Revised concept of text generation with transformers.
DAY 37: Revised concept of prompt engineering.
DAY 38: Intro to decison trees.
DAY 39: Intro to clustering.
DAY 40: Learned about K-means clustering.
DAY 41: Learned about optimising K-means algorithm.
DAY 42: Experimented with prompt engineering.
DAY 43: Introduction to anamoly detection.
DAY 44: Revised concept of Normal distribution.
DAY 45: Learned to build Anamoly detection algorithm.
DAY 46: Learned the difference between Anamoly detection vs supervised learning and choosing features.
DAY 47: Introduction to Recommender Systems.
DAY 48: Learned about collaborative filterng and implementing Recommender systems using tensorflow.
DAY 49: Learned the differences between Collaborative filtering and Content baded filtering.
DAY 50: Learned implementation of Collaborative filtering using neural networks and with tensor flow.
DAY 51: Learned the concept and implementation of PCA.
DAY 52: Reviewed reinforcement learning and learned about state action value function with example of a rover landing on moon.
DAY 53: Introduction to reinforcement learning with human feedback for LLMs.
DAY 54: Learned about variational graph auto encoders.
DAY 55: Learned about VAEs vs VGAEs.
DAY 56: Learned about techniques used to get better accuracy on ML models.
DAY 57: Learned about data imputation techniques.
DAY 58: Explorer various feature engineering techniques.
DAY 59: Worked on Digit recognizer.
DAY 60: Learned about fine tuning LLMs.
DAY 61: Learned about dealing with imbalanced datasets.
DAY 62: Introduction to AutoML.
DAY 63: Worked on digit recognition.
DAY 64: Revised multi head attention concept with calculation.
DAY 65: Learned about ways to enhance nueral network trainings with methods like Batch Normalization and so.
DAY 66: Revised some interesting pandas methods.
DAY 67: Learned about some interesting python libraries like pydantic, hypothesis, etc.
DAY 68: Learned about time series forecasting and methods to implement it.
DAY 69: Tips about reading research papers and learned to use Jupyter better with extensions
DAY 70: Active Learning strategies
DAY 71: Explored the code for the project "Predicting Credit Card Approvals using Machine Learning"
DAY 72: Explored ways to fill missing data with Python.
DAY 73: Explored the concept of uplift modelling.
DAY 74: Explored Visualizations in Multivariate cases.
DAY 75: Explored Neural Network embeddings and visualizations.
DAY 76: Explored the process of installing Hugging face transformers.
DAY 77: Read medium article on Churn Analysis.
DAY 78: Read medium article on analysing and calculating p-value.
DAY 79: Read medium article on NLP RELIC
DAY 80: Read medium article about Plotly and using it for creating interactive visualizations.
DAY 81: Read medium article about scraping linkedin profiles and using Langchain.
DAY 82: Read medium article about EDA.
DAY 83: Read medium article about Grokking.
DAY 84: Read medium article about Data imputation.
DAY 85: Read Medium article about Decision tree classifier.
DAY 86: Read Medium article about Time series forecasting with Transformers.
DAY 87: Read Medium article about using Pyspark for data analysis.
DAY 88: Read Medium article about Time Series Forecasting with TimeMixer.
DAY 89: Read Medium article on Deploying Machine learning model.
DAY 90: Read Medium article on Scaling Numerical features.
DAY 91: Read Medium article on Sarcasm detection with NLP.
DAY 92: Followed turorial on trend detection on Kaggle.
DAY 93: Followed turorial on trend detection on Kaggle.
DAY 94: Followed turorial on trend detection on Kaggle.
DAY 95: Read Medium article on Cleaning the data for NLP tasks.
DAY 96: Did Exercise on Time series forecasting on kaggle.
DAY 97: Read Medium article on GPU requirements for LLMs.
DAY 98: Read Medium article on Hybrid Classifiers in Time Series.
DAY 99: Read Medium article on Stacking with ensemble models.
DAY 100: Read Medium article on ensemble methods.
DAY 101: Read Medium arricle on automated feature engineering with featuretools.
DAY 102: Read Medium article on stacking ml methods.
DAY 103: Read Medium article on implementing transformers with pytorch.
DAY 104: Read Medium article on K-L Divergence.
DAY 105: Read Medium article on feature engineering.
DAY 106: Did exercise on Time series forecasting on Kaggle.
DAY 107: Studied K fold and stratified validation.
DAY 108: Read Medium article on implementing PCA.
DAY 109: Read Medium article comparing Linear Regression, XG-Boost and Gaussian Preditions.
DAY 110: Read Medium article about P values.
DAY 111: Read Medium article about Classification project.
DAY 112: Read Medium article about Boltzmann Machines.
DAY 113: Read Medium article on San fransisco crime classification EDA.
DAY 114: Read Medium article on dockerizing machine learning model.
DAY 115: Read Medium article on SQL functions for data analysis.
DAY 116: Read Medium article on running LLAMA on local machine.
DAY 117: Read Medium article on A/B testing in Data Science
DAY 118: Worked on San Francisco crime dataset challenge on kaggle.
DAY 119: Read Medium article on deploying ML models with docker.
DAY 120: Read Medium article on SMOTE
DAY 121: Read Medium article on Thompson Sampling and one arm bandit.
DAY 122: Read Medium article on Logistic Regression.
DAY 123: Read Medium article on Downloading amd transcribing Youtube Videos.
DAY 124: Read Medium article on Featuretools.
DAY 125: Read Medium article on ARIMA.
DAY 126: Read Medium article on using LLMs and Retrieval Augmented Classification for classification tasks.
DAY 127: Revised several data science concepts.
DAY 128: Revised different types of Classification algorithms.
DAY 129: Read Medium article on Latest research papers on Machine Learning.
DAY 130: Read Medium article about Movie reccomender system
DAY 131: Read Medium article about addressing missing data.
DAY 132: Read Medium article about Bayesian Inference.
DAY 133: Read Medium article on fitting the best machine learning model
DAY 134: Read Medium article on Customer segmentation
DAY 135: Read Medium article on RAG and embedding models.
DAY 136: Read Medium article on Machine Learning project lifecycle
DAY 137: Read Medium article on Metrics in Machine Learning
DAY 138: Read Medium article on Supermarket sales project
DAY 139: Read Medium article on AI stack in current world
DAY 140: Read Medium article on EDA using the library ydata-profiling.
DAY 141: Read Medium article on using different Pandas functions
DAY 142: Read Medium article on PyCaret library.
DAY 143: Read Medium article on Dynamic RAG.
DAY 144: Read Medium article on important Machine Learning Models.
DAY 145: Read Medium article on XGBoost algo.
DAY 146: Read Medium article on Tensorflow vs PyCharm
DAY 147: Read Medium article on Lifecycle of an ML Model
DAY 148: Read Medium article on Bagging and Boosting.
DAY 149: Read Medium article on comparing classification models.
DAY 150: Read Medium article on Bayes Theorem
DAY 151: Read Medium article on SHAP
DAY 152: Read Medium article on Low Rank Transformations of LLM
DAY 153: Read Medium article on Fine Tuning LLMs
DAY 154: Read Medium article on PCA
DAY 155: Read Medium article on Python libraries for AI tasks
DAY 156: Read Medium article on using FRONNI library for calculating performance metrics
DAY 157: Read Medium article on using sklearn pipelines
DAY 158: Read Medium article on logistic regression
DAY 159: Read Medium article on Model Calibration.
DAY 160: Read Medium article on Fine Tuning Llama with Lora
DAY 161: Read Medium article on training Deepseek R1 and GRPO method.
DAY 162: Read Medium article on Anthropic using 2 classifier models along with the main llm to make it unbreakable.
DAY 163: Read Medium article on fine tuning flux model on our images.
DAY 164: Read Medium article on statistical methods in data science.
DAY 165: Read Medium article on training reasoning models like o1 and R1.
DAY 166: Read Medium article on better looking plots for data visualizations.
DAY 167: Read Medium article on making better looking bar plots.
DAY 168: Read Medium article on Agentic Reasoning.
DAY 169: Read Medium article on KAG.
DAY 170: Read Medium article on python libraries.
DAY 171: Read Medium article on MLFlow
DAY 172: Read Medium article on myths of AI
DAY 173: Read Medium article on data analytics using different charts.
DAY 174: Read Medium article on Bootstrapping Bagging and Boosting.
DAY 175: Read Medium article on Large Concept Models.
DAY 176: Read Medium article on CNN vs ANN
DAY 177: Read Medium article on Chain of Draft prompting.
DAY 178: Read Medium article on Gittok.dev
DAY 179: Read Medium article on MLOps
DAY 180: Read Medium article on Python production code practices.
DAY 181: Researched on PHDs
DAY 182: Read Medium article on Data Analysis. Learned about a very interesting chart called sunburst chart.
DAY 183: Read about Manus AI agent.
DAY 184: Read about AI Engineering: Prompting.
DAY 185: Read about AI Engineering: RAG.
DAY 185: Read about AI Engineering: Agents.
DAY 186: Read about using LLMs and RAGs with CBR for a phd role.
DAY 187: Read more about LLMs and RAGs with CBR
DAY 188: READ THE PAPER AGAIN. GAVE INTERVIEW. GOT PHD GRANT.
DAY 189: Read medium article on building audience on medium.
DAY 190: Did Kaggle GenAI intensive course day 1: Prompting.
DAY 191: Skimmed medium article about AI Engineering.
DAY 192: Read about tech behind GPT4o's native image generation.
DAY 192: Read the research paper on GPT4o's native image generation.
Day 193: Read Medium article on Anatomy of LLMs. how they neuron firing happens when they predict the next work. Fascinating
DAY 194: Read Medium article on Google Data Science agent.
DAY 195: Read Medium article on Google A2A agent protocol and about a python library called Python A2A. Very interesting read.
DAY 196: Read Medium article on using Gpt4o for different image generation use cases.
DAY 197: Read Medium article on usinf different RAG techniques.
DAY 198: Read Medium article on Open Source Ai agents stack amd tools.
DAY 199: Read Medium arricle about good ML practices.
DAY 200: Read Medium article about good prompting methods.
DAY 201: Read Medium article about AI agents.
DAY 202: Read Medium article on Dspy.
DAY 203: Read Medium article on using NotebookLM to increasing productivity and learning.
DAY 204: Read Medium article about staying relevant as a data scientist.
DAY 205: Watched youtube videos on MLOps
DAY 206: Read medium article about using agents to code.
DAY 207: Read medium article about using SEAL architecture to self tune llms.
DAY 208: Read medium article about making chatgpt less of a yes man.
DAY 209: Read medium article about why LLMs hallucinate. apparently its because of the way they are trained.
DAY 210: Read medium article about MCP servers
DAY 211: Read medium article on identifying best classification model based on calibration scores.
DAY 212: Read medium article on using AI with efficient note taking to provide more context.
DAY 213: Read medium article on Claude 4.5 sonnet
DAY 214: Read medium article on SORA 2 and its effects and about MCP servers
DAY 215: Read medium article on claude 4.5
DAY 216: Watched videos on agentic AI and read about working with Agents.
DAY 217: Read Medium article on opportunities to build AI based products.
DAY 217: Read Medium article on URL context grounding and its relevance to RAG.
DAY 218: Read Medium article on using AI model better for coding.
DAY 219: Read Medium article on the infamous MIT article stating 95% failure rate in organisations using AI.
DAY 220: Read Medium article on using AI to write better
DAY 221: Read Medium article on new Deepseek OCR model.
DAY 222: Read Medium article on a useful prompting strategy.
DAY 223: Read Medium article on building projects with several agents.
DAY 223: Read Medium article on building MCP servers for ChatGPT
DAY 224: Read several medium articles on tech, science, history and geography.
DAY 225: Read Medium article on MCP servers and Claude's new skills feature.
DAY 226: Read Medium article on Google's Transformer 2.0 paper
DAY 227 Read article on building rag system without hallucinations
DAY 228: Read medium article on scaling laws and what to expect in 2026 for llms.
DAY 229: Read Medium article on LLM pretraining post training and alignment.
DAY 230: Read Medium article on looped transformers
DAY 231: Read Medium article on NotebookLM
DAY 232: Read Medium article on Deepseek engrams model.
DAY 233: Read Medium article on Claude code and its new course.
DAY 234: Read Medium article on multi agentic workflows and agent tools.
DAY 235: Read Medium article on creating MCP servers