Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/rohit077/100_Days_of_ML
Machine Learning is the most transformative technology of our time. Whether its helping us discover new drugs for major diseases, fighting fraud, generating music, improving supply chain efficiency, the list of applications are truly endless. In order for us as a community to be able to make valuable contributions to the world, we need to master this technology. This is a call to action, a battle cry, a spark that will light a movement to radically improve the state of humanity. 100 Days of ML Code is a committment to better your understanding of this powerful tool by dedicating at least 1 hour of your time everyday to studying and/or coding machine learning for 100 days.
https://github.com/rohit077/100_Days_of_ML
Last synced: 28 days ago
JSON representation
Machine Learning is the most transformative technology of our time. Whether its helping us discover new drugs for major diseases, fighting fraud, generating music, improving supply chain efficiency, the list of applications are truly endless. In order for us as a community to be able to make valuable contributions to the world, we need to master this technology. This is a call to action, a battle cry, a spark that will light a movement to radically improve the state of humanity. 100 Days of ML Code is a committment to better your understanding of this powerful tool by dedicating at least 1 hour of your time everyday to studying and/or coding machine learning for 100 days.
- Host: GitHub
- URL: https://github.com/rohit077/100_Days_of_ML
- Owner: rohit077
- License: mit
- Created: 2020-06-23T06:01:45.000Z (about 4 years ago)
- Default Branch: master
- Last Pushed: 2023-02-16T01:52:05.000Z (over 1 year ago)
- Last Synced: 2024-02-18T06:33:26.485Z (4 months ago)
- Language: Jupyter Notebook
- Size: 8.91 MB
- Stars: 2
- Watchers: 2
- Forks: 4
- Open Issues: 6
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Lists
- awesome-resources - Python, Machine Learning, Tensorflow, Deep Learning
README
# 100_Days_of_ML
This is 100 days of Machine Learning challenge as instructed by [Siraj Raval](https://github.com/llSourcell/100_Days_of_ML_Code) #learningbydoing
# Motivation
Machine Learning is the most transformative technology of our time. Whether its helping us discover new drugs for major diseases, fighting fraud, generating music, improving supply chain efficiency, the list of applications are truly endless. In order for us as a community to be able to make valuable contributions to the world, we need to master this technology. This is a call to action, a battle cry, a spark that will light a movement to radically improve the state of humanity. 100 Days of ML Code is a commitment to better your understanding of this powerful tool by dedicating at least 1 hour of your time everyday to studying and/or coding machine learning for 100 days.
# Daily Log
It's the daily log to keep track on my progress.
# Day 1 : June 25, 2020 | Overview
1. Today I got the overview of Machine Learning Algorithms with the Mind-maps and Cheat sheets.
2. Set up the environment(anaconda.org) to complete this challenge and also completed choosing the courses I will follow.
Link to Progress - [Overview](https://github.com/rohit077/100_Days_of_ML/tree/master/Overview)
# Day 2 : June 26, 2020 | Linear Regression
1. Learnt the basics of Linear Regression and revisited the Machine Learning Course by Andrew Ng in Coursera. Alternative free course - [Stanford YT](https://www.youtube.com/watch?v=4b4MUYve_U8&list=PLoROMvodv4rMiGQp3WXShtMGgzqpfVfbU&index=3&t=2218s)
2. Implemented Linear Regression without using popular Libraries and Frameworks on the 'bike_sharing_data.csv'.
Link to Progress - [Linear Regression with NumPy and Python](https://github.com/rohit077/100_Days_of_ML/tree/master/Linear_Regression)
# Day 3 : June 27, 2020 | Logistic Regression
1. Learnt the basic intuition of Logistic Regression and enrolled to the [guided project](https://www.coursera.org/projects/logistic-regression-numpy-python) on Logistic Logistic Regression.
2. Implemented Logistic Regression using Python.
Link to Progress - [Logistic Regression with Numpy](https://github.com/rohit077/100_Days_of_ML/blob/master/Logistic_Regression/Logistic_Regression_with_NumPy_.py)
# Day 4 : June 28, 2020 | Better Intuition of Regression
1. Continued with Regression and Coursera ML Course.
2. Tried Implementing Linear Regression with [Siraj Raval's tutorial](https://www.youtube.com/watch?v=XdM6ER7zTLk&t=1928s)
Link to Progress - [How to Do Linear Regression using Gradient Descent](https://github.com/llSourcell/linear_regression_live/blob/master/demo.py)
# Day 5 : June 29, 2020 | Descending into ML
1. Enrolled into a free course offered by Google - [Machine Learning Crash Course](https://developers.google.com/machine-learning/crash-course) and completed upto [First steps with Tensorflow](https://developers.google.com/machine-learning/crash-course/first-steps-with-tensorflow/programming-exercises).
Link to Progress - [First Steps with TF: Programming Exercises](https://developers.google.com/machine-learning/crash-course/first-steps-with-tensorflow/programming-exercises)
# Day 6: June 30, 2020 | Regression with a Real Dataset
1. Continued the ML crash curse by [google](https://developers.google.com/machine-learning/crash-course)
2. Implemented Linear Regression with Real Dataset in [Google Colab](https://colab.research.google.com/)
Link to Progress - [Linear regression with tf.keras](https://github.com/rohit077/100_Days_of_ML/blob/master/Linear_Regression/Linear%20Regression%20with%20a%20Real%20Dataset.ipynb)
# Day 7 : July 1, 2020 | COVID19 Data Analysis
1. Today I analyzed Covid-19 Dataset using python on real dataset.
2. I took the data and completed the project with help of [Rhyme Project Network](https://www.coursera.org/learn/covid19-data-analysis-using-python/home/welcome)
Link to Progress - [COVID-19 Data Analysis](https://github.com/rohit077/100_Days_of_ML/blob/master/COVID-19%20Data%20Analysis/COVID19%20Data%20Analysis%20Using%20Python.py)
# Day 8 : July 2, 2020 | Machine Learning Crash Course
1. Completed the ML course upto [Validation Set](https://developers.google.com/machine-learning/crash-course/validation/check-your-intuition)
2. Enrolled into Project centric course - [Predicting House Prices with Regression using TensorFlow](https://www.coursera.org/learn/tensorflow-beginner-predicting-house-prices-regression/home/welcome)
Link to Progress - [Housing Price Prediction](commit)
# Day 9 : July 3, 2020 | Predicting House Prices with Regression
1. Implemented Housing Price Prediction with [Boston_housing.csv](https://www.kaggle.com/sagarnildass/predicting-boston-house-prices?select=housing.csv#Getting-Started) data.
Link to Progress - [Housing Price Prediction](https://github.com/rohit077/100_Days_of_ML/blob/master/Predicting%20Housing%20Prices/Predicting%20House%20Prices%20with%20Regression.ipynb)
# Day 10 : July 4, 2020 | Predicting Profit of Food Truck
1. Predicted Profit of Food Truck with Regression with the previous data given by assignment page.
2. I Implemented Linear regression with single variable from scratch.
Link to Progress - [Food Truck Profit Prediction](https://github.com/rohit077/100_Days_of_ML/blob/master/Predicting%20Housing%20Prices/Predicting%20House%20Prices%20with%20Regression.ipynb)
# Day 11 : July 5, 2020 | CS50’s Introduction to AI with Python
1. Enrolled into the CS50's AI course(audit) to freshen up with [HarvardX: CS50AI](https://www.edx.org/course/cs50s-introduction-to-artificial-intelligence-with-python).
2. Explored with the Source code of the Maze from first lecture, the code is provided in the link below.
Link to Progress - [Maze](https://github.com/rohit077/100_Days_of_ML/blob/master/HarvardX%20CS50AI/maze.py)
# Day 12 : July 6, 2020 | Project 0
1. Completed the quiz and the project part after the first lecture.
Link to Progress - [projects/2020/x/degrees](https://github.com/rohit077/100_Days_of_ML/tree/master/HarvardX%20CS50AI)
# Day 13 : July 7, 2020 | Flight Fare Prediction
1. Today, I Implemented Flight Price Prediction after watching the live stream by [Krish Naik](https://www.youtube.com/watch?v=6vqGeigbwjc&t=2447s)
2. Learnt more about the data pre-processing from YouTube.
Link to Progress - [Flight_price](https://github.com/rohit077/100_Days_of_ML/blob/master/Flight%20Fare%20Prediction.ipynb)
# Day 14 : July 8, 2020 | Baseline: Data, ML
1. Completed the Baseline: Data, ML, AI Quest upto [DataProc](https://google.qwiklabs.com/focuses/585?parent=catalog)
2. Continued with [CS50:AI](https://courses.edx.org/courses/course-v1:HarvardX+CS50AI+1T2020/course/)
Link to Progress - [Baseline: Data, ML, AI](https://google.qwiklabs.com/quests/34)
# Day 15 : July 9, 2020 | RandomForest classifier, Decision Trees
1. Learned How to use Scikit-learn implementing this [Project: Predict Employee Turnover with scikit-learn](https://www.coursera.org/learn/employee-turnover-scikit-learn/home/week/1).
Link to Progress - [Predicting Employee Turnover with scikit-learn](https://www.coursera.org/learn/employee-turnover-scikit-learn/resources/c3Evg).
# Day 16 : July 10, 2020 | Qwiklab ML Quest
1. Finished the following quest - [Perform Foundational Data, ML, and AI Tasks in Google Cloud.](https://www.qwiklabs.com/quests/117)
2. Learned a lot new things and how to implemented them in gcp, it's a great hand's on learning platform.
Link to Progress - [Data, ML, and AI Tasks in Google Cloud](https://www.qwiklabs.com/public_profiles/13780136-a403-4d9a-8762-41935e83695f).
# Day 17 : July 11, 2020 | Titanic Survival Prediction
1. Get my hand dirty with the [Titanic Survival Data](https://www.kaggle.com/c/titanic/data).
2. Submitted my first [kaggle submission](https://www.kaggle.com/c/titanic/submissions).
Link to Progress - [Titanic: Machine Learning from Disaster](https://github.com/rohit077/100_Days_of_ML/blob/master/Titanic%20Survival%20Prediction/kernel36239a5421.ipynb).
# Day 18 : July 12, 2020 | House Prices: Advanced Regression Techniques
1. Exploring the dataset from [kaggle](https://www.kaggle.com/c/home-data-for-ml-course/data).
2. continuing the competition with [Krish Naik](https://www.youtube.com/channel/UCNU_lfiiWBdtULKOw6X0Dig).
Link to Progress - [Advance House Price Prediction](https://github.com/krishnaik06/Kaggle-Competitions).
# Day 19 : July 13, 2020 | Predicting Sales with Advertising Dataset
1. Implemented Multiple [Linear Regression with scikit-learn](https://www.coursera.org/learn/scikit-learn-multiple-linear-regression/home/welcome) in Coursera.
2. Coursera Network platform is a great place to learn by praticing real-time with tutorials & datasets.
Link to Progress - [Predicting-sales-with-multiple-linear-regression](https://github.com/rohit077/100_Days_of_ML/tree/master/Linear%20Regression/Multiple%20Linear%20Regression).
# Day 20 : July 14, 2020 | House Prices: Advanced Regression Techniques
1. Completed upto data preprocessing with [krishnaik06](https://www.youtube.com/channel/UCNU_lfiiWBdtULKOw6X0Dig).
2. Kaggle Competition - [House Prices: Advanced Regression Techniques](https://www.youtube.com/watch?v=vtm35gVP8JU&t=412s).
Link to Progress - [Advance House Price Prediction](https://www.kaggle.com/rohitroychowdhury0/kernel54800cfd13).
# Day 21 : July 15, 2020 | Kaggle Competition
1. Submitted yesterday's progress along with deployment.
2. Edited the model with hyperparameter tuning.
Link to Progress - [kaggle submission: Housing Prices Advanced Regression](https://github.com/rohit077/100_Days_of_ML/blob/master/Predicting%20Housing%20Prices/kernel54800cfd13.ipynb).
# Day 22 : July 16, 2020 | Car Price Prediction from CarDekho Dataset
1. Predicting Car Prices from [Vehicle dataset from cardekho](https://www.kaggle.com/nehalbirla/vehicle-dataset-from-cardekho) with [@krishnaik06](https://www.youtube.com/channel/UCNU_lfiiWBdtULKOw6X0Dig).
2. Completed upto model deployment part, will update the front-end by tommorow.
Link to Progress - [Car Price Prediction](https://github.com/rohit077/100_Days_of_ML/tree/master/Car%20Price%20Prediction)
# Day 23 : July 17, 2020 | Machine Learning Feature Selection
1. Learnt more of Feature Selection in depth from [Coursera Project Network](https://www.coursera.org/learn/machine-learning-feature-selection-in-python/ungradedLti/BDxG6/machine-learning-feature-selection-in-python).
Link to Progress - [](.).
# Day 24 : July 18, 2020 | fast.ai
1. Enrolled into the most recommended open sourced course and completed up-to Random Forest.
2. Random Forest is widely applicable ml model, You can find it here: [lec. 1](http://course18.fast.ai/lessonsml1/lesson1.html).
Link to Progress - []()
# Day 25 : July 19, 2020 | First ML project
1. I choose to complete at least four projects by the end of 100_Days_of_ML_Code by all alternative 25'th day.
2. As I previously worked on some Housing Price Predictions, starting with a similar data - [Delhi Real-Estate Prices by MagicBricks.com](https://www.kaggle.com/neelkamal692/delhi-house-price-prediction).
Link to Progress - [Delhi Housing Price Prediction](https://github.com/rohit077/100_Days_of_ML/blob/master/Delhi%20Housing%20Price%20Prediction/Delhi%20Housing%20Price%20Prediction%20-%20Magicbricks.ipynb).
# Day 26 : July 20, 2020 | Deployment with Heroku
1. Deployed the machine learning model.pkl with [Heroku](https://dashboard.heroku.com/).
2. Fixed some issues and improved the accuracy a little bit.
Link to Progress - [Delhi Real-estate Price Prediction](https://real-estate-price.herokuapp.com/).
# Day 27 : July 21, 2020 | Improving Front-End
1. Learnt basic html and css as I've no prior experience with Front-end.
2. CS50's web Programming course is a great resource to learn.
Link to Progress - [CS50's Web Development](https://cs50.harvard.edu/web/2020/).
# Day 28 : July 22, 2020 | Invoking Machine Learning API's
1. Enrolled into Google Machine Learning Specialization Course and completed upto modeule 3.
2. Exploring Rest API's from Qwicklab.
Link to Progress - [How Google does Machine Learning](https://www.coursera.org/learn/google-machine-learning).
# Day 29 : July 23, 2020 | Hyperparameter Tuning with Diabetes dataset
1. Finished yesterday's course - How Google Does Machine Learning.
2. Joined the live class by Krish Naik on hyperparameter-tuning with diabetes data.
Link to Progress - [Hyper Parameter Tuning](https://github.com/rohit077/100_Days_of_ML/tree/master/Hyper%20Parameter%20Tuning).
# Day 30 : July 24, 2020 | Launching into Machine Learning
1. Completed upto Decision Trees and re-visited archived courses to note-making for future self XD.
Link to Progress - Check Resources Column
# Day 31 : July 25, 2020 | CS229: Stanford
1. Taking notes of CS229: Machine Learning, this is great alternative of Coursera's Andrew Ng ml course.
2. Continuing with the epic Fast.ai course and finished [Launching into Machine Learning](https://www.coursera.org/learn/launching-machine-learning) course.
Link to Progress - [CS229: Machine Learning](http://cs229.stanford.edu/).
# Day 32 : July 26, 2020 | Pima Indians Diabetes Database
1. Prediction of Diabetes Dataset on kaggle done with RandomForestRegressor.
2. Follow Krish Naik's Live project videos to learn more - [Diabetes Prediction using Machine Learning](https://www.youtube.com/watch?v=HTN6rccMu1k&t=406s)
Link to Progress - []()
# Day 33 : July 27, 2020 | Problem Set 1
1. Submitted the first Problem Set of [CS50AI](https://www.edx.org/course/cs50s-introduction-to-artificial-intelligence-with-python).
Link to Progress - []()
# Day 34 : July 28, 2020 | TensorFlow
1. Started Intro to TensorFlow from Qwicklab and completed first two lab with basic operations.
2. Brushing up python with NumPy and Panda.
Link to Progress - []()
# Day 35 : July 29, 2020 | Intro to TensorFlow
1. Continuing the GCP course on TensorFlow, the course is well structured but beginner friendly.
Link to Progress - []().
# Day 36 : July 30, 2020 | Cab Price Prediction
1. Predicted the cab price data with Linear Regression and DNN, got rmse < 10.
2. This one is the part of the course assignment, the notebook is available in the following link.
Link to Progress - [training-data-analyst](https://github.com/GoogleCloudPlatform/training-data-analyst/blob/master/courses/machine_learning/deepdive/03_tensorflow/d_traineval.ipynb).
# Day 37 : July 31, 2020 | Deployment using Cloud AI platform
1. Scaling up cab price model.py file using Cloud AI Platform on GCP.
2. This is also part course assignment, check this [repo](https://github.com/GoogleCloudPlatform/training-data-analyst/blob/master/courses/machine_learning/deepdive/03_tensorflow/e_ai_platform.ipynb).
Link to Progress - [Scaling up ML using Cloud AI Platform](https://github.com/GoogleCloudPlatform/training-data-analyst/blob/master/courses/machine_learning/deepdive/03_tensorflow/e_ai_platform.ipynb).
# Day 38 : August 1, 2020 | Implementing Decision Tree
1. A decision tree is a flowchart-like structure in which each internal node represents a "test" on an attribute, each branch represents the outcome of the test, and each leaf node represents a class label.
Link to Progress - [Classification Trees in Python, From Start To Finish](https://www.coursera.org/learn/classification-trees-in-python/home/welcome).
# Day 39 : August 2, 2020 | Moving Into DL
1. Started learning Deep Learning with the MIT Deep Learning Playlist available on YouTube.
2. Completed the first task of assignment - 1, [Deep learning basics](https://www.youtube.com/watch?v=O5xeyoRL95U&list=PLrAXtmErZgOeiKm4sgNOknGvNjby9efdf&index=2&ab_channel=LexFridman).
Link to Progress - [Boston Housing Price Prediction with FFNN](https://github.com/lexfridman/mit-deep-learning/blob/master/tutorial_deep_learning_basics/deep_learning_basics.ipynb).
# Day 40 : August 3, 2020 | Planar data classification with a hidden layer
1. Continuing the epic Deep Learning course thought by Andrew Ng.
2. Finished the 3'rd week's assignment on Planar data classification with a hidden layer.
Link to Progress - [Planar data classification with a hidden layer]().
# Day 41 : August 4, 2020 | Neural Network from Scratch
1. 1. In week 4 of deeplearning.ai course, built a Neural Network from scratch.
Link to Progress - [Building Deep Neural Network](https://www.coursera.org/learn/neural-networks-deep-learning/notebook/lSYZM/building-your-deep-neural-network-step-by-step).
# Day 42 : August 5, 2020 | Intro to TensorFlow
1. Completed the first assignment of MIT6.S191, thaught by [Alexander Amini](https://www.youtube.com/watch?v=njKP3FqW3Sk&list=PLtBw6njQRU-rwp5__7C0oIVt26ZgjG9NI&index=2&t=242s&ab_channel=AlexanderAmini).
2. The part - 1 describes basic operations in TensorFlow and the aumated differentiation.
Link to Progress - [Intro to TensorFlow](https://github.com/aamini/introtodeeplearning/blob/master/lab1/solutions/Part1_TensorFlow_Solution.ipynb).
# Day 43 : August 6, 2020 | Recognition of Digits using CNN
1. Completed the second part of assignment-1 of Lex Fridman DL [Lectures](https://www.youtube.com/playlist?list=PLrAXtmErZgOeiKm4sgNOknGvNjby9efdf).
2. It build the overview of how hand written digits can be recognised using CNN.
Link to Progress - [Classification of MNIST Dreams with Convolutional Neural Networks](https://github.com/lexfridman/mit-deep-learning/blob/master/tutorial_deep_learning_basics/deep_learning_basics.ipynb).
# Day 44 : August 7, 2020 | Qwicklab
1. Continued with unfinished qwicklabs, then explored different GitHub repos.
Link to Progress - [Intro to ML](https://www.qwiklabs.com/public_profiles/13780136-a403-4d9a-8762-41935e83695f).
# Day 45 : August 8, 2020 | Two layer Neural Network for Classification
1. Implemented a two layer neural network for
Link to Progress - [Implementation of neural network from scratch](https://www.educba.com/implementation-of-neural-networks/).
# Day 46 : August 9, 2020 | Appen Platform
1. Appen is a platform that provides or improves data used for the development of machine learning and artificial intelligence. Basically, it's a paid data annotation platform.
Link to Progress - [Appen](https://appen.com/).
# Day 47 : August 10, 2020 | Kaggle Course Completion
1. Completed kaggle's Intro to ML course. Kaggle courses are great for fundamentals as well as state of the art topics.
Link to Progress - [kaggle learn](https://www.kaggle.com/learn/overview).
# Day 48 : August 11, 2020 | 'HE' Initialization
1. Initialized 'HE' for better intuition.
2. Follow this [blog](https://datascience.stackexchange.com/questions/13061/when-to-use-he-or-glorot-normal-initialization-over-uniform-init-and-what-are) to learn more.
Link to Progress - [Qwiklab](https://www.qwiklabs.com/public_profiles/13780136-a403-4d9a-8762-41935e83695f).
# Day 49 : August 12, 2020 | First Neural Net with Tensorflow
1. Build Neural Network from Scratch in TensorFlow in Coursera Project Network.
2. Applied the neural network model to solve a multi-class classification problem.
Link to Progress - [Neural Network from Scratch in TensorFlow](https://www.coursera.org/projects/neural-network-tensorflow).
# Day 50 : August 13, 2020 | Generating Music with LSTM
1. Working on my Second Project - Getting Hans Zimmer music with LSTM.
Link to Progress - []()
# Day 51 : August 14, 2020 | Implementing Dropout
1. Back to deeplearning.ai coursework. working on the assignment.
Link to Progress - [deeplearning-ai](https://www.coursera.org/deeplearning-ai)
# Day 52 : August 15, 2020 |
Link to Progress - []()
# Day 53 : August 16, 2020 |
Link to Progress - []()
# Day 54 : August 17, 2020 |
Link to Progress - []()
# Day 55 : August 18, 2020 |
Link to Progress - []()
# Day 56 : August 19, 2020 |
Link to Progress - []()
# Day 57 : August 20, 2020 |
Link to Progress - []()
# Day 58 : August 21, 2020 |
Link to Progress - []()
# Day 59 : August 22, 2020 |
Link to Progress - []()
# Day 60 : August 23, 2020 |
Link to Progress - []()
# Day 61 : August 24, 2020 | Hand-Tuning
1. Improved model accuracy by hand-tuning hyperparameters in qwiklabs.
Link to Progress - []()
# Day 62 : August 25, 2020 | Hyperparameter Tuning
1. Hyperparameter tuning on housing prices dataset on gcloud.
Link to Progress - []()
# Day 63 : August 26, 2020 | Neural Network
1. Finished the qwiklab quest Using Neural Network to Build AI Model.
2.
Link to Progress - []()
# Day 64 : August 27, 2020 | Cat vs. Dog
1. In this rhyme interface predicted if a image is containing Dogs or Cats using Resnet50.
Link to Progress - []()
# Day 65 : August 28, 2020 | Transfer Learning
1. Predicting the signs on the basis of Day __, with Transfer Learning.
Link to Progress - []()
# Day 66 : August 29, 2020 | Using Custom Estimator in Time-Series
1.In this Coursera project,
2.
Link to Progress -
# Day 67 : August 30, 2020 | Auto-encoders
1. Reducing image noises with auto-encoders in TensorFlow.
2. This [rhyme interface](https://www.coursera.org/learn/image-noise-reduction-auto-encoders/home/welcome) developed the understanding of auto-encoders.
Link to Progress -
# Day 68 : August 31, 2020 | Traffic Sign Recognition with Keras
1. Converted images to grayscale, performed normalization, then applied CNN to it.
2. This [rhyme course](https://www.coursera.org/learn/traffic-sign-classification-deep-learning/home/welcome) is one of the most useful as it's a great project of computer vision.
Link to Progress -
# Day 69 : September 1, 2020 | Image Compression with K-Means Clustering
1. Today I learnt k-means clustering and applied it to compress images.
2. This Coursera Project is most useful so far.
Link to Progress -
# Day 70 : September 2, 2020 | What-If Tool with Image Recognition Models
1. Detecting Smiles in Images with What-if Tool in qwiklabs.
Link to Progress - [What-If Tool with Image Recognition Models](https://www.qwiklabs.com/focuses/10904?parent=catalog).
# Day 71 : September 3, 2020 | Predicting Heart Disease with Decision Trees
1. Build a Classification Tree, which uses continuous and categorical data from the UCI Machine Learning Repository to predict whether or not a patient has heart disease.
Link to Progress [Classification Trees in Python, From Start To Finish](https://www.coursera.org/learn/classification-trees-in-python/home/welcome).
# Day 72 : September 4, 2020 | Implementing Convolution Layer
1. So, this is the first assignment of CNN course by deeplearning.ai, the lectures are very useful, also available on their YouTube channel.
2. Implemented single Convolution layer from scratch.
Link to Progress - [Convolutional Model: step by step](https://www.coursera.org/learn/convolutional-neural-networks/notebook/7XDi8/convolutional-model-step-by-step).
# Day 73 : September 5, 2020 | Convolutional model Application
1. Completed the second assignment of CNN (deeplearning.ai).
2.
Link to Progress - [Convolutional model: application](https://www.coursera.org/learn/convolutional-neural-networks/programming/bwbJV/convolutional-model-application).
# Day 74 : September 6, 2020 | Deeplearning for Coders
1. Started the epic Fast.ai course-v4 - [Deeplearning For Coders](https://youtu.be/_QUEXsHfsA0).
2. I used google colab to follow the course, check the documentation if faced any error in setup.
Link to Progress -
# Day 75 : September 7, 2020 | Tomato Disease
1. Got 84% accuracy on predicting Tomato leaf diseases.
2. The tutorial is avaible on [here](https://www.youtube.com/watch?v=chQNuV9B-Rw&t=12s) if you wish to follow along.
Link to Progress -
# Day 76 : September 8, 2020 | Keras
1. Predicted signs with Resnet50 in Keras, it's the optional assignment of deeplearning.ai cnn course.
2. check out the repo to follow along with the Keras tutorial.
Link to Progress -
# Day 77 : September 9, 2020 | Object Detection with YOLO
1. Continuing with previous day, completed week 3 assignment, detecting cars with YOLO algorithm.
Link to Progress -
# Day 78 : September 10, 2020 | Face Recognition
1. Implemented face verification and recognition with Inception model.
2. Though it's the second part of the week 4, completed it as the lecture part of the Neural style transfer isn't completed.
Link to Progress -
# Day 79 : September 11, 2020 | Art Generation with AI
1. Finished CNN course of deeplearning.ai with the final assignment. The assignments are great for the future projects as well.
2.
Link to Progress -
# Day 80 : September 12, 2020 | Face Detection
1. Build a face detector for my squad with small dataset, thanks to augmentation.
2.
Link to Progress -
# Day 81 : September 13, 2020 | Facial Recognition with SVM
1. Get hand's on the rhyme interface to build a facial recognition system with SVM.
Link to Progress -
# Day 82 : September 14, 2020 | LSTM
1. Build a RNN from scratch as the week 1 programming assignment of deeplearning.ai final course.
Link to Progress -
# Day 83 : September 15, 2020 | NLP
1. Implemented NLP to make a Shakesphere Model using Recurrent Neural Network.
Link to Progress -
# Day 84 : September 16, 2020 | Improvising Jazz with LSTM
1. This is the week 2 Programming assignment of Sequence model, created a jazz music with LSTM.
Link to Progress -
# Day 85 : September 17, 2020 | Flower Classification
1. Classiflying flowers with Inception V3.
2.
Link to Progress -
# Day 86 : September 18, 2020 | Autoencoders
1. Sharpening Images with Autoencoders.
2.
Link to Progress -
# Day 87 : September 19, 2020 | Making Emojis with NLP
1. Completed week 2 assignment of the deeplearning.ai sequence model course.
2.
Link to Progress -
# Day 88 : September 20, 2020 | Sentiment Analysis with IMDB
1. Analysing sentiments of movie reviews of IMDB dataset.
2.
Link to Progress -
# Day 89 : September 21, 2020 | Fake News Detection
1. Detecting fake news with NLP.
2.
Link to Progress -
# Day 90 : September 22, 2020 | Trigger Word Detection
1. Trigger Word Datection - it's the final course assignment of deeplearning.ai; it's the single best course to learn ML in depth.
2. Tried to implement this on my local machine but failed.
Link to Progress -
# Day 91 : September 23, 2020 | Sentiment Analysis
1. Twitter Sentiment Analysis in Kaggle, do check out my kernel & drop a comment as it's my first try with NLP.
2.
Link to Progress -
# Day 92 : September 24, 2020 | Language Classification
1. In this rhyme project network, classified language with the help of NLP.
2.
Link to Progress -
# Day 93 : September 25, 2020 | FIFA 2020
1. Explored the FIFA 2020 Dataset available on the project repo to practice some EDA on it.
2.
Link to Progress -
# Day 94 : September 26, 2020 | Customer Market Segmentation
1. Leant the use of Unsupervised Learning in this coursera project network.
2.
Link to Progress -
# Day 95 : September 27, 2020 | Data Science Track
1. Started the Data Science Track on the GCP using qwiklabs.
2. Completed this on purpose of getting the swags of 30 Days of Google Cloud Challenge on October.
Link to Progress -
# Day 96 : September 28, 2020 | Prediction on Chest X-Rays
1. Predicting on Chest X-Ray Dataset to perform the
2.
Link to Progress -
# Day 97 : September 29, 2020 | Deepfakes
1. Generating deepfakes with keras.
2.
Link to Progress -
# Day 98 : September 30, 2020 | K-Means Clustering
1.
Link to Progress -
# Day 99 : October 1, 2020 | Facial Expression Classification
1. Performing facial expression classification with Resnet50 in Coursera Project Network.
2.
Link to Progress -
# Day 100 : October 2, 2020 | Debiasing
1. Finally it's done, it's a long long & long journey to me as nobody is guiding me here, found some repos but that's doesn't attracted me.
2. Learned a lot in this journey, skipped alot which I will update from now on for sure.
Link to Progress -
## Do drop a star if it help you or inspire you any bit. Thanks for visiting.