AI Rank
← 开源
campusx-official

ML-Roadmap-for-2022

A curated list of Machine learning videos, links, projects and datasets to help you conquer the ML landscape in 6 months

TutorialsMLE roadmap
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
1.24k
Star
579
Fork
+3
本周
2
贡献者
创建于 2022-01-10 · 更新于 2026-10-13 · 今日第 11030 名
主要开发者
campusx-officialnitishksingh24

campusx-official/ML-Roadmap-for-2022 排名第 11,030，有 1,235 个星标。

同类别比较

campusx-official/ML-Roadmap-for-2022 排名第 11,030，此处有 8 个同类条目；dsgiitr/graph_nets 排名第 11,025。

同类别比较
名称排名指标
wangyuGithub01/Machine_Learning_Resources11,001
星标数:
1,242
分叉数:
179
简介:
:fish::fish::fish: 机器学习面试复习资源
Hyperparticle/one-pixel-attack-keras11,008
语言:
Jupyter Notebook
星标数:
1,240
分叉数:
214
简介:
Keras implementation of "One pixel attack for fooling deep neural networks" using differential evolution on Cifar10 and ImageNet
mlbvn/ml-yearning-vi11,012
语言:
Python
星标数:
1,239
分叉数:
396
简介:
Một cuốn sách tập trung vào hướng dẫn cách cấu trúc các dự án Học Máy và phân tích cách làm cho các thuật toán Học Máy hoạt động.
dsgiitr/graph_nets11,025
语言:
Jupyter Notebook
星标数:
1,236
分叉数:
226
简介:
PyTorch Implementation and Explanation of Graph Representation Learning papers: DeepWalk, GCN, GraphSAGE, ChebNet & GAT.
MorvanZhou/Evolutionary-Algorithm11,035
语言:
Python
星标数:
1,234
分叉数:
618
简介:
Evolutionary Algorithm using Python, 莫烦Python 中文AI教学
the-full-stack/fsdl-text-recognizer-project11,057
语言:
Jupyter Notebook
星标数:
1,229
分叉数:
421
简介:
Lab materials for the Full Stack Deep Learning Course
hanbt/learn_dl11,075
语言:
TeX
星标数:
1,225
分叉数:
971
简介:
Deep learning algorithms source code for beginners
ml4a/ml4a-ofx11,080
语言:
C++
星标数:
1,224
分叉数:
272
简介:
A collection of openFrameworks apps for working with machine learning
关键参数与规格
关键参数与规格
参数值
类别Tutorials
子类别MLE roadmap
星标数1,235
分叉数579
贡献者2
创建日期2022-01-10
更新日期2026-10-13
1 天星标数0
7 天星标数3
排名11,030
上次排名10,987
排名变化-43
7 天星标排名7,006
上次 7 天星标排名6,205
7 天星标排名变化-801
总星标排名9,472
上次总星标排名9,466
总星标排名变化-6
国家India
README 摘录

ML-Roadmap-for-2022 A curated list of Machine learning videos, links, projects and datasets to help you conquer the ML landscape in 6 months Levels of Learning 1. time 6-8 Weeks) The goal of this level is to get you familiar with the ML universe. #### Learn Exploratory Data Analysis (EDA) (Est. #### Learn Machine Learning Basics (Est. time 6-8 Weeks) The goal of this level is to learn the core machine learning concepts and algorithms 1. time 6

-8 Weeks) The goal of this level is to get you introduced to the practical side of machine learning. What you learn at this level would really help you out there in the wild. #### Feature Scaling/Normalization (Est. #### Modelling - Stacking and Blending (Est. time 6-8 Weeks) This is the level where you would dive into different domains of Machine Learning. Mastering these will make you a true Data Scientist. #### Fundamentals of Neural Network - 5. time 6-8 Weeks) The

objective of this level is to sharpen your knowledge that you have accumulated in the previous 4 levels 1. 8 types of Projects for your portfolio - 2.

常见问题

记录了多少星标和分叉？

campusx-official/ML-Roadmap-for-2022 有 1,235 个星标和 579 个分叉。

仓库排名是多少？

campusx-official/ML-Roadmap-for-2022 排名第 11,030。

哪个仓库排名最接近？

campusx-official/ML-Roadmap-for-2022 与 dsgiitr/graph_nets 比较，后者排名第 11,025，有 1,236 个星标。

README

ML-Roadmap-for-2022

A curated list of Machine learning videos, links, projects and datasets to help you conquer the ML landscape in 6 months

Levels of Learning

  1. Testing the waters

  2. Gaining Conceptual depth

  3. Learning Practical Concepts

  4. Diving into different domains

  5. Pushing it with Projects

1. Testing the waters (Est. time 6-8 Weeks)

The goal of this level is to get you familiar with the ML universe. You will learn a bit of everything.

  1. Learn Python (Est. time - 2 weeks)

     1. Basics of Python - https://www.youtube.com/playlist?list=PLKnIA16_Rmvb1RYR-iTA_hzckhdONtSW4
 2. OOP in Python
    - Lecture 1 - https://www.youtube.com/watch?v=1s869EfxoDo
    - Lecture 2 - https://www.youtube.com/watch?v=8To-A6VPL90
 3. Advance Topics
    - File Handling - https://www.youtube.com/watch?v=ixEeeNjjOJ0
    - Exception Handling - https://www.youtube.com/watch?v=NIWwJbo-9_8
    - Regular Expressions - https://www.youtube.com/watch?v=K8L6KVGG-7o
    - Functional Programming - https://www.youtube.com/watch?v=SvK_GErE2nM
    - Basics of Flask - https://www.youtube.com/watch?v=swHI1H7DVsQ
 4. Practice Problems - https://docs.google.com/document/d/1E_xCNijOWZ4Bm7r7DVj-1OA-oUopEFmv4tRm0YNuFWQ/edit?usp=sharing

  2. Learn Numpy (Est. time 3 Days)

     1. Numpy Playlist - https://www.youtube.com/watch?v=CpPLLp3snK4&list=PLKnIA16_Rmvb-ToL3RQ_bwxG4_ND-0-DT
 2. Numpy Practice Problems - https://github.com/rougier/numpy-100

  3. Learn Pandas (Est. time 4 Days)

     1. Pandas Playlist - https://www.youtube.com/watch?v=kq9Vmg5d7Sk&list=PLKnIA16_RmvbR85fgbfVRKOiMokUKVupy
 2. Pandas Problems - https://github.com/ajcr/100-pandas-puzzles

  4. Learn Data Visualization (Est. time 1 Week)

     1. Matplotlib - https://www.youtube.com/playlist?list=PL-osiE80TeTvipOqomVEeZ1HRrcEvtZB_
 2. Seaborn - https://www.youtube.com/playlist?list=PLKnIA16_RmvbB1bFGjvS6a8T0mnqawejo

  5. Descriptive Statistics (Est. time 4 Days)

     1. Statistics Playlist - https://www.youtube.com/watch?v=tPhzDKjQBpo&list=PLKnIA16_RmvbVrE0eZO2bCaFln6jaNq-1

  6. Learn Data Analysis Process (Est. time 1 week)

     1. Playlist - https://www.youtube.com/watch?v=ZhacwtUR0SU&list=PLKnIA16_RmvZAqJzKstVHywcRNMn6pcGD

  7. Learn Exploratory Data Analysis (EDA) (Est. time 1 Week)

    1. Understanding your data - https://www.youtube.com/watch?v=mJlRTUuVr04
2. Univariate Analysis - https://www.youtube.com/watch?v=4HyTlbHUKSw
3. Bivariate and Multivariate Analysis - https://www.youtube.com/watch?v=6D3VtEfCw7w
4. Pandas Profiling - https://www.youtube.com/watch?v=E69Lg2ZgOxg
5. EDA on House Prices Dataset - https://www.kaggle.com/pmarcelino/comprehensive-data-exploration-with-python
6. EDA on Titanic Dataset - https://www.kaggle.com/startupsci/titanic-data-science-solutions
7. EDA on Haberman's Survival Dataset - https://www.kaggle.com/gokulkarthik/haberman-s-survival-exploratory-data-analysis
8. EDA on Heart Disease Dataset - https://www.kaggle.com/kralmachine/analyzing-the-heart-disease
9. EDA on IPL Dataset - https://www.kaggle.com/ash316/let-s-play-cricket
10. EDA on Wine Review Dataset - https://www.kaggle.com/kabure/wine-review-s-eda-recommend-systems
11. EDA on PIMA Diabetes Dataset - https://www.kaggle.com/shrutimechlearn/step-by-step-diabetes-classification-knn-detailed
12. EDA on Breast Cancer Dataset - https://www.kaggle.com/kanncaa1/statistical-learning-tutorial-for-beginners
13. EDA on Olympics Dataset - https://www.youtube.com/watch?v=5nQXhusiu7s
14. EDA on Covid Data - https://www.youtube.com/watch?v=ll0aZVNnOP8
15. WhatsApp Chat Analysis Project - https://www.youtube.com/watch?v=Q0QwvZKG_6Q

  8. Learn Machine Learning Basics (Est. time 1 Week)

     1. What is Machine Learning? https://www.youtube.com/watch?v=ZftI2fEz0Fw
 2. AI vs ML vs DL https://www.youtube.com/watch?v=1v3_AQ26jZ0
 3. Types of Machine Learning - https://www.youtube.com/watch?v=81ymPYEtFOw
 4. Batch Machine Learning - https://www.youtube.com/watch?v=nPrhFxEuTYU
 5. Online Machine Learning - https://www.youtube.com/watch?v=3oOipgCbLIk
 6. Instance based vs Model based learning - https://www.youtube.com/watch?v=ntAOq1ioTKo
 7. Challenges in Machine Learning - https://www.youtube.com/watch?v=WGUNAJki2S4
 8. Applications of Machine Learning - https://www.youtube.com/watch?v=UZio8TcTMrI
 9. Machine Learning Development Lifecycle - https://www.youtube.com/watch?v=iDbhQGz_rEo
 10. Data Engineer V Data Analyst V Data Scientist V ML Engineer - https://www.youtube.com/watch?v=93rKZs0MkgU
 11. How to frame a Machine Learning problem? - https://www.youtube.com/watch?v=A9SezQlvakw
 12. Installing and using software for data science - https://www.youtube.com/watch?v=82P5N2m41jE
 13. How to work with CSV files? - https://www.youtube.com/watch?v=a_XrmKlaGTs
 14. Working with JSON and SQL data - https://www.youtube.com/watch?v=fFwRC-fapIU
 15. Building an End to End Machine Learning Project - https://www.youtube.com/watch?v=dr7z7a_8lQw

2. Gaining Conceptual depth (Est. time 6-8 Weeks)

The goal of this level is to learn the core machine learning concepts and algorithms

  1. Learn about tensors (Est. time - 1 Day)

     1. What are Tensors? - https://www.youtube.com/watch?v=vVhD2EyS41Y

  2. Advance Statistics

     1. Covariance
 2. Pearson Correlation Coefficient
 3. QQ Plot
 4. Confidence Interval
 5. Hypothesis Testing
 6. Chisquare Test, Anova Test
 7. Playlist link - https://www.youtube.com/watch?v=qtaqvPAeEJY&list=PLKnIA16_Rmvbe9wDJGXc28KKr6lp5Jn2g

  3. Probability Basics

     1. Conditional Probability
 2. Independent Events
 3. Bayes Theorem
 4. Uniform Distribution
 5. Binomial Distribution
 6. Bernaulli Distribution
 7. Poission Distribution
 8. Playlist Link - https://www.youtube.com/watch?v=Ty7knppVo9E&list=PLKnIA16_RmvYNbPMB6ofVLRCcTPUAftdY

  4. Linear Algebra Basics

     1. Representing Tabular Data
 2. Vectors
 3. Matrices
 4. Matrix Multiplication
 5. Dot Product
 6. Equation of line in N-dim
 7. Eigen Vector and Eigen Values
 8. Playlist Link - https://www.youtube.com/watch?v=e9h-ZZ_ahRg&list=PLKnIA16_RmvYu0fS_RuIB2eTbJcTFdrAA

  5. Basics of Calculus

     1. Big Picture of Derivatives
 2. Maxima and Minima
 3. Playlist link - (first 4 videos only) https://www.youtube.com/playlist?list=PLBE9407EA64E2C318

  6. Machine Learning Algorithms

     1. Linear Regression - https://www.youtube.com/watch?v=UZPfbG0jNec&list=PLKnIA16_Rmva-wY_HBh1gTH32ocu2SoTr
 2. Gradient Descent - https://www.youtube.com/watch?v=ORyfPJypKuU&list=PLKnIA16_RmvZvBbJex7T84XYRmor3IPK1
 3. Logistic Regression - https://www.youtube.com/watch?v=XNXzVfItWGY&list=PLKnIA16_Rmvb-ZTsM1QS-tlwmlkeGSnru
 4. Support Vector Machines - https://www.youtube.com/watch?v=ugTxMLjLS8M&list=PLKnIA16_RmvbOIFee-ra7U6jR2oIbCZBL
 5. Naive Bayes - https://www.youtube.com/watch?v=Ty7knppVo9E&list=PLKnIA16_RmvZ67wQaHoBuzXaDAfPz-a6l
 6. K Nearest Neighbors - https://www.youtube.com/watch?v=BYaoDZM1IcU&list=PLKnIA16_RmvZiE-lEdN5RDi18-u-T43zd
 7. Decision Trees - https://www.youtube.com/watch?v=gwgmSSTdiXs&list=PLKnIA16_RmvYGY_n9PP8zN-0LG9MoZRjU
 8. Random Forest - https://www.youtube.com/watch?v=bHK1fE_BUms&list=PLKnIA16_RmvZyqP3WGUo7iVziIIea_1bp
 9. Bagging - https://www.youtube.com/watch?v=LUiBOAy7x6Y&list=PLKnIA16_RmvZ7iKIcJrLjUoFDEeSejRpn
 10. Adaboost - https://www.youtube.com/watch?v=sFKnP0iP0K0&list=PLKnIA16_RmvZxriy68dPZhorB8LXP1PY6
 11. Gradient Boosting - https://www.youtube.com/watch?v=fbKz7N92mhQ&list=PLKnIA16_RmvaMPgWfHnN4MXl3qQ1597Jw
 12. Xgboost - https://www.youtube.com/watch?v=BTLB-ppqBZc&list=PLKnIA16_RmvbXJbBW4zCy4Xbr81GRyaC4
 13. Principle Component Analysis (PCA) - https://www.youtube.com/watch?v=ToGuhynu-No&list=PLKnIA16_RmvYHW62E_lGQa0EFsph2NquD
 14. KMeans Clustering - https://www.youtube.com/watch?v=5shTLzwAdEc&list=PLKnIA16_RmvbA_hYXlRgdCg9bn8ZQK2z9
 15. Heirarchical Clustering - https://www.youtube.com/watch?v=Ka5i9TVUT-E
 16. DBSCAN - https://www.youtube.com/watch?v=RDZUdRSDOok
 17. T-sne - https://www.youtube.com/watch?v=NEaUSP4YerM and https://distill.pub/2016/misread-tsne/

  7. Machine Learning Metrics - https://www.youtube.com/watch?v=Ti7c-Hz7GSM&list=PLKnIA16_RmvZJGOqRjqhOhTEmQW3vDdbQ

  8. Bias Variance Tradeoff - https://www.youtube.com/watch?v=74DU02Fyrhk

  9. Regularization - https://www.youtube.com/watch?v=aEow1QoTLo0&list=PLKnIA16_RmvZuSEZ24Wlm13QpsfLlJBM4

  10. Cross-Validation - https://www.youtube.com/watch?v=S5NkE-xgx98

3. Learn Practical Concepts (Est. time 6-8 Weeks)

The goal of this level is to get you introduced to the practical side of machine learning. What you learn at this level would really help you out there in the wild.

  1. Data Acquisition (Est. time - 2 Days)

     1. Web Scraping - https://www.youtube.com/watch?v=8NOdgjC1988
         * Project - Create a Pandas dataframe of Indian cuisines from some website using web scraping.
 2. Fetch data from API - https://www.youtube.com/watch?v=roTZJaxjnJc
         * Project - Create a Pandas dataframe of movies from TMDB API.

  2. Working with missing values (Est. time - 3 Days)

     1. Complete Case Analysis - https://www.youtube.com/watch?v=aUnNWZorGmk
 2. Handling missing numerical data - https://www.youtube.com/watch?v=mCL2xLBDw8M
 3. Handling missing categorical data - https://www.youtube.com/watch?v=l_Wip8bEDFQ
 4. Missing indicator - https://www.youtube.com/watch?v=Ratcir3p03w
 5. KNN Imputer - https://www.youtube.com/watch?v=-fK-xEev2I8
 6. MICE - https://www.youtube.com/watch?v=a38ehxv3kyk
 7. Kaggle Notebooks and Practice Datasets - https://docs.google.com/document/d/1_9Y6kxNc6QTym2Y2JGEBbnCUbE1qZWLVzVXlT2eX_FQ/edit?usp=sharing

  3. Feature Scaling/Normalization (Est. time - 2 Days)

     1. Standarization - https://www.youtube.com/watch?v=1Yw9sC0PNwY
 2. Normalization - https://www.youtube.com/watch?v=eBrGyuA2MIg

  4. Feature Encoding Techniques (Est. time - 2 Days)

     1. Ordinal Enconding and Label Encoding - https://www.youtube.com/watch?v=w2GglmYHfmM
 2. One Hot Encoding - https://www.youtube.com/watch?v=U5oCv3JKWKA
 3. Encoding high cardinality categorical features - https://www.kaggle.com/general/16927
 4. Feature hashing - https://datasciencestunt.com/dealing-with-categorical-features-with-high-cardinality-feature-hashing/

  5. Feature Transformation(Est. time - 2 Days)

     1. Log Transform - https://www.youtube.com/watch?v=cTjj3LE8E90
 2. Box Cox Transform - https://www.youtube.com/watch?v=lV_Z4HbNAx0
 3. Yeo Johnson Transform - https://www.youtube.com/watch?v=lV_Z4HbNAx0
 4. Discretization - https://www.youtube.com/watch?v=kKWsJGKcMvo

  6. Working with Pipelines(Est. time - 2 Days)

    1. Column Transformer - https://www.youtube.com/watch?v=5TVj6iEBR4I
2. Sklearn Pipelines - https://www.youtube.com/watch?v=xOccYkgRV4Q

  7. Handing Time and Date data(Est. time - 1 Day)

    1. Working with time and date data - https://www.youtube.com/watch?v=J73mvgG9fFs

  8. Working with Outliers (Est. time - 3 Days)

    1. What are Outliers? - https://www.youtube.com/watch?v=Lln1PKgGr_M
2. Outlier detection and removal using Z-score method - https://www.youtube.com/watch?v=OnPE-Z8jtqM
3. Outlier detection and removal using IQR method - https://www.youtube.com/watch?v=Ccv1-W5ilak
4. Percentile method - https://www.youtube.com/watch?v=bcXA4CqRXvM

  9. Feature Construction (Est. time - 1 Day)

    1. Feature Construction - https://www.youtube.com/watch?v=ma-h30PoFms

  10. Feature Selection (Est. time - 3 Days)

     1. Feature selection using SelectKBest and Recursive Feature Elimination - https://www.youtube.com/watch?v=xlHk4okO8Ls&t=1s
 2. Chi-squared Feature Selection - https://www.youtube.com/watch?v=fMIwIKLGke0
 3. Backward Feature Elimination - https://www.youtube.com/watch?v=zW1SvA0Z-l4&t=2s
 4. Dropping features using Pearson correlation coefficient - https://www.youtube.com/watch?v=FndwYNcVe0U
 5. Feature Importance using Random Forest - https://www.youtube.com/watch?v=R47JAob1xBY
 6. Feature Selection Advise - https://www.youtube.com/watch?v=YaKMeAlHgqQ

  11. Cross Validation (Est. time - 2 Days)

     1. What is cross-validation? - https://www.youtube.com/watch?v=fSytzGwwBVw
 2. Holdout Method - https://www.youtube.com/watch?v=4NnI3SBuww4
 3. K-Fold Cross Validation - https://www.youtube.com/watch?v=gJo0uNL-5Qw
 4. Leave 1 Out Cross Validation - https://www.youtube.com/watch?v=yxqcHWQKkdA
 5. Time series cross validation - https://www.youtube.com/watch?v=g9iO2AwTXyI

  12. Modelling - Stacking and Blending (Est. time - 1 Week)

     1. Stacking - https://www.youtube.com/watch?v=O-aDHBGMqXA
 2. Blending - https://www.youtube.com/watch?v=TuIgtitqJho
 3. LightGBM - https://www.youtube.com/watch?v=n_ZMQj09S6w
 4. CatBoost - https://www.youtube.com/watch?v=8o0e-r0B5xQ

  13. Model Tuning (Est. time - 4 Days)

     1. GridSearchCV - https://www.youtube.com/watch?v=4Im0CT43QxY
 2. RandomSearchCV - https://www.youtube.com/watch?v=Q5dH5mOQ_ik
 3. Hyperparameter Tuning - https://www.youtube.com/watch?v=355u2bDqB7c

  14. Working with imbalanced data (Est. time - 3 Days)

     1. How to handle imbalanced data - https://www.youtube.com/watch?v=JnlM4yLFNuo
 2. Kaggle Notebook - https://www.kaggle.com/kabure/credit-card-fraud-prediction-rf-smote
 3. SMOTE on Quora Dataset - https://www.kaggle.com/theoviel/dealing-with-class-imbalance-with-smote

  15. Handling Multicollinearity(Est. time - 2 Days)

     1. What is multicollinearity? - https://www.youtube.com/watch?v=ekuD8JUdL6M
 2. Practical Example - https://www.youtube.com/watch?v=ATH4urDitI8
 3. VIF in Multicollinearity - https://www.youtube.com/watch?v=GMAp_tP1ZQ0

  16. Data Leakage - (Est. time - 2 Days)

     1. What is Data Leakage? - https://machinelearningmastery.com/data-leakage-machine-learning/
 2. Practical - Data Leakage on Quora Question Pair Dataset - https://www.kaggle.com/sudalairajkumar/simple-leaky-exploration-notebook-quora
 3. Practical - Data Leakage on Credit Card data - https://www.kaggle.com/dansbecker/data-leakage

  17. Serving your model(Est. time - 1 Week)

     1. Pickling your model - https://www.youtube.com/watch?v=yY1FXX_GSco
 2. Flask Tutorial - https://www.youtube.com/watch?v=swHI1H7DVsQ
 3. Streamlit Tutorial - https://www.youtube.com/watch?v=Klqn--Mu2pE
 4. Deploy model on Heroku - https://www.youtube.com/watch?v=YncZ0WwxyzU
 5. Deploy model on AWS - https://www.youtube.com/watch?v=_rwNTY5Mn40
 6. Deploy model to GCP - https://www.youtube.com/watch?v=fw6NMQrYc6w
 7. Deploy model to Azure - https://www.youtube.com/watch?v=qnbJcbjh-3s
 8. ML model to Android App - https://www.youtube.com/watch?v=ax3WyB-_LJY

  18. Working with Large Datasets

     1. What is Out of core ML? - https://www.youtube.com/watch?v=9e4nUuq2Hmg
 2. Practical implementation of Out of core ML - https://www.youtube.com/watch?v=sRCuvcdvuzk
 3. NYC Cab Dataset Project - https://vaex.io/blog/ml-impossible-train-a-1-billion-sample-model-in-20-minutes-with-vaex-and-scikit-learn-on-your

4. Diving into different domains (Est. time 6-8 Weeks)

This is the level where you would dive into different domains of Machine Learning. Mastering these will make you a true Data Scientist.

  1. SQL (Est. time - 2 Days)

     1. Complete SQL Roadmap - https://www.youtube.com/watch?v=FGBme8dWR_M
 2. SQL learning resources - https://docs.google.com/document/d/1wCALgWubTOvuvlXJ3Eweh7AgJj4sPq2pW92y3viPZbs/edit?usp=sharing
 3. The only video you need to see - https://www.youtube.com/watch?v=nopIGY1zJE0

  2. Recommendation Systems

     1. Movie Recommendation System - https://www.youtube.com/watch?v=1xtrIEwY_zY
 2. Book Recommender System - https://www.youtube.com/watch?v=sf93xpq8vaA
 3. Fashion Recommender System - https://www.youtube.com/watch?v=xanJe6e8Xuw

  3. Association Rule Learning

     1. Association Rule Mining(Apriori Algorithm) - https://www.youtube.com/watch?v=guVvtZ7ZClw
 2. Eclat Algorithm - https://www.youtube.com/watch?v=oBiq8cMkTCU
 3. Market Basket Analysis - https://www.youtube.com/watch?v=Y7Xkqqfz1UU

  4. Anamoly Detection

     1. Anamoly Detection Lecture from Microsoft Research - https://www.youtube.com/watch?v=12Xq9OLdQwQ
 2. Novelty Detection Lecture - https://www.youtube.com/watch?v=vIDcjbpwY3k

  5. NLP

     1. Complete NLP Roadmap - https://www.youtube.com/watch?v=PKv_okm1H-k
 2. Complete NLP Playlist - https://www.youtube.com/watch?v=zlUpTlaxAKI&list=PLKnIA16_RmvZo7fp5kkIth6nRTeQQsjfX
 3. NLP Project Ideas - https://www.youtube.com/watch?v=oWJe2T29kAo
 4. Email Spam Classifier Project - https://www.youtube.com/watch?v=YncZ0WwxyzU
 5. Building a Chatbot - https://www.youtube.com/watch?v=Nb21OhaW8GY

  6. Time Series(Coming Soon)

  7. Computer Vision(Coming Soon)

  8. Fundamentals of Neural Network - https://www.youtube.com/playlist?list=PLKnIA16_RmvYuZauWaPlRTC54KxSNLtNn

5. Pushing it with Projects (Est. time 6-8 Weeks)

The objective of this level is to sharpen your knowledge that you have accumulated in the previous 4 levels

  1. 8 types of Projects for your portfolio - https://www.youtube.com/watch?v=SQHfry4xmdM
  2. How to select a project - https://www.youtube.com/watch?v=kH--k1VKFt4
  3. Car Price Predictor - https://www.youtube.com/watch?v=iRCaMnR_bpA
  4. Banglore House Price Predictor - https://www.youtube.com/watch?v=DVxkI1VmpCk
  5. Posture Detection using ML5.js - https://www.youtube.com/watch?v=kRvIcdLhDtU
  6. Laptop Price Predictor - https://www.youtube.com/watch?v=BgpM2IiCH6k
  7. Which bollywood celebrity are you? - https://www.youtube.com/watch?v=X67rclJcIL0
  8. Finding similar GOT characters - https://www.youtube.com/watch?v=ygGknomFEWY
  9. IPL win probability predictor - https://www.youtube.com/watch?v=ygGknomFEWY
  10. T20 score predictor - https://www.youtube.com/watch?v=ygGknomFEWY
  11. Titanic Survivor Prediction - https://www.youtube.com/watch?v=Bnp94fpxZjY
  12. Diabetes Prediction using ML - https://www.youtube.com/watch?v=xUE7SjVx9bQ
  13. Fake news prediction - https://www.youtube.com/watch?v=nacLBdyG6jE
  14. Loan Status Prediction - https://www.youtube.com/watch?v=XckM1pFgZmg
  15. Gold Price Prediction - https://www.youtube.com/watch?v=9ffkBvh8PTQ
  16. Handwriting Classifier - https://www.youtube.com/watch?v=1B3YIkyPNk0
  17. Flight Fare Prediction - https://www.youtube.com/watch?v=y4EMEpEnElQ
  18. Link for 500+ ML+DL projects - https://github.com/ashishpatel26/500-AI-Machine-learning-Deep-learning-Computer-vision-NLP-Projects-with-code
排名相邻
同类项目