YouTube Tools
Support

Krish Naik's Complete Deep Learning Playlist: study plan and how long it takes

The Krish Naik playlist is 88 videos and 30.4 hours long. Here's how long it takes at different paces, a week-by-week schedule built from the real videos, and a planner that turns it into your own daily plan.

88 videos · 30.4 hours · Krish Naik

Krish Naik's deep learning playlist covers neural network basics, vanishing gradients, optimizers, CNNs, RNNs and LSTMs, attention and transformers, and many applied projects: stock price prediction, audio classification, face detection and pose estimation.

It mixes tutorials and live sessions, so video lengths vary a lot.

Who it's for: Learners who want deep learning theory plus lots of applied project walkthroughs.

How long does it take?

The full playlist is 30.4 hours across 88 videos. Here's roughly how many days that is at different daily watch times and speeds, counting video time only:

Days to finish the playlist by daily watch time and playback speed
Daily timeAt 1xAt 1.5xAt 2x
30 min a day61 days41 days31 days
1 h a day31 days21 days16 days
2 h a day16 days11 days8 days

Make your own schedule

The playlist link is already filled in. Press Plan, set how much time you have each day and your speed, and you'll get a day-by-day schedule with a finish date and a calendar file. It reads the live playlist, so new videos are included.

Open on YouTube Track watched videos

Week-by-week schedule

A sample plan at 1 hour a day and normal speed, using whole videos so none is split across days. That's 5 weeks in total. For a different pace, start date or speed, use the planner above.

Week 1Videos 1–20 · 5h 3m

  1. Day 1 · 30m

    • 1Why Deep Learning Is Becoming So Popular?🔥🔥🔥🔥🔥🔥14m
    • 2Complete Road Map To Prepare For Deep Learning🔥🔥🔥🔥16m

  2. Day 2 · 59m

    • 3Introduction To Machine Learning And Deep Learning For Starters50m
    • 4Tutorial 1- Introduction to Neural Network and Deep Learning8m

  3. Day 3 · 51m

    • 5Tutorial 2- How does Neural Network Work7m
    • 6Tutorial 3-Activation Functions Part-16m
    • 7Tutorial 4: How to train Neural Network with BackPropogation9m
    • 8Tutorial 5- How to train MultiLayer Neural Network and Gradient Descent14m
    • 9Tutorial 6-Chain Rule of Differentiation with BackPropagation14m

  4. Day 4 · 50m

    • 10Tutorial 7- Vanishing Gradient Problem15m
    • 11Tutorial 8- Exploding Gradient Problem in Neural Network11m
    • 12Tutorial 9- Drop Out Layers in Multi Neural Network12m
    • 13Tutorial 10- Activation Functions Rectified Linear Unit(relu) and Leaky Relu Part 212m

  5. Day 5 · 52m

    • 14Deep Learning-Activation Functions-Elu, PRelu,Softmax,Swish And Softplus39m
    • 15Tutorial 11- Various Weight Initialization Techniques in Neural Network13m

  6. Day 6 · 53m

    • 16Tutorial 12- Stochastic Gradient Descent vs Gradient Descent12m
    • 17Tutorial 13- Global Minima and Local Minima in Depth Understanding14m
    • 18Tutorial 14- Stochastic Gradient Descent with Momentum13m
    • 19Tutorial 15- Adagrad Optimizers in Neural Network13m

  7. Day 7 · 9m

    • 20Tutorial 16- AdaDelta and RMSprop optimizer9m
Week 2Videos 21–42 · 7h 52m

  1. Day 8 · 1h 42m

    • 21Deep Learning-All Optimizers In One Video-SGD with Momentum,Adagrad,Adadelta,RMSprop,Adam Optimizers1h 42m

  2. Day 9 · 1h 43m

    • 22Session On Different Types Of Loss Function In Deep Learning1h 43m

  3. Day 10 · 55m

    • 23Tutorial 17- Create Artificial Neural Network using Weight Initialization Tricks25m
    • 24Keras Tuner Hyperparameter Tuning-How To Select Hidden Layers And Number of Hidden Neurons In ANN19m
    • 25Tutorial 18- Hyper parameter Tuning To Decide Number of Hidden Layers in Neural Network11m

  4. Day 11 · 56m

    • 26Tutorial 19- Training Artificial Neural Network using Google Colab GPU19m
    • 27Tutorial 20- Convolution Neural Network vs Human Brain7m
    • 28Tutorial 21- What is Convolution operation in CNN?11m
    • 29Tutorial 22- Padding in Convolutional Neural Network8m
    • 30Tutorial 23- Operation Of CNN(CNN vs ANN)11m

  5. Day 12 · 49m

    • 31Tutorial 24- Max Pooling Layer In CNN7m
    • 32Tutorial 25- Data Augmentation In CNN-Deep Learning8m
    • 33Tutorial 26- Create Image Dataset using Data Augmentation using Keras-Deep Learning-Data Science7m
    • 34Tutorial 27- Create CNN Model and Optimize using Keras Tuner- Deep Learning28m

  6. Day 13 · 49m

    • 35Tutorial 28- Create CNN Model Using Transfer Learning using Vgg 16, Resnet15m
    • 36Tutorial 29- Why Use Recurrent Neural Network and Its Application10m
    • 37Tutorial 30- Recurrent Neural Network Forward Propogation With Time11m
    • 38Tutorial 31- Back Propagation In Recurrent Neural Network8m
    • 39Tutorial 32- Problems In Simple Recurrent Neural Network6m

  7. Day 14 · 58m

    • 40Tutorial 33- Installing Cuda Toolkit And cuDNN For Deep Learning20m
    • 41Tutorial 34- LSTM Recurrent Neural Network In Depth Intuition23m
    • 42Word Embedding - Natural Language Processing| Deep Learning15m
Week 3Videos 43–54 · 5h 52m

  1. Day 15 · 54m

    • 43Implementing Word Embedding Using Keras- NLP | Deep Learning18m
    • 44Develop your Neural Network Like A Google Deep Learning Developer14m
    • 45Kaggle Faker News Classifier Using LSTM- Deep LEarning| Natural Language Processing22m

  2. Day 16 · 44m

    • 46Stock Price Prediction And Forecasting Using Stacked LSTM- Deep Learning37m
    • 47Bidirectional RNN Indepth Intuition- Deep Learning Tutorial8m

  3. Day 17 · 31m

    • 48Implement Kaggle Fake News Classifier Using Bidirectional LSTM RNN18m
    • 49Sequence To Sequence Learning With Neural Networks| Encoder And Decoder In-depth Intuition13m

  4. Day 18 · 50m

    • 50Develop Your First Deep Learning End To End Project As A Beginner In Data Science in 30 minutes31m
    • 51Encoder And Decoder- Neural Machine Learning Language Translation Tutorial With Keras- Deep Learning19m

  5. Day 19 · 11m

    • 52Problems With Encoders And Decoders- Indepth Intuition11m

  6. Day 20 · 1h 4m

    • 53Live Session- Understanding Attention Models Architecture And Maths Intuition- Deep Learning1h 4m

  7. Day 21 · 1h 38m

    • 54Live Session- Encoder Decoder,Attention Models, Transformers, Bert Part 11h 38m
Week 4Videos 55–71 · 6h 54m

  1. Day 22 · 1h 36m

    • 55Live- Attention Models, Transformers In depth Intuition Deep Learning- Part 21h 36m

  2. Day 23 · 1h 19m

    • 56Live -Transformers Indepth Architecture Understanding- Attention Is All You Need1h 19m

  3. Day 24 · 48m

    • 57How To Train Deep Learning Models In Google Colab- Must For Everyone24m
    • 58Alexnet Architecture In-depth-Discussion Along With Code-Deep Learning Advanced CNN23m

  4. Day 25 · 1h

    • 59VGGNET Architecture In-depth Discussion Along With Code -Deep Learning Advanced CNN24m
    • 60Hummingbird-Run Traditional Machine Learning model on Deep Neural Network frameworks-Data Science14m
    • 61Lets Implement LSTM RNN Models For Univariate Time Series Forecasting- Deep Learning22m

  5. Day 26 · 50m

    • 62TensorDash- How To Monitor Your Deep Learning Model Metrics, Loss, Accuracy Using Mobile App13m
    • 63Handling Imbalanced Dataset Using Cost Sensitive Neural Networks- Credit Card Fraud Detection16m
    • 64500+ Machine Learning And Deep Learning Projects All At One Place8m
    • 65Google Colab Pro Vs Colab Free- Benefits Of Using Colab Pro- How To Access From India13m

  6. Day 27 · 39m

    • 66How To Implement Image Classification Using SVM In Convolution Neural Network16m
    • 67Object Localization Vs Object Detection Deep Learning16m
    • 683000+ Research Datasets For Machine Learning Researchers By Papers With Code7m

  7. Day 28 · 44m

    • 69PerceptiLabs-The Best Machine Learning Visual Modeling Tool-Train Deep Learning Neural Network28m
    • 70Face Recognition Attendance Based Project In Machine Learning10m
    • 71Colab Pro Now Available In India, Brazil, France, Thailand,Japan,UK- BOON FOR Data Science Aspirants6m
Week 5Videos 72–88 · 4h 40m

  1. Day 29 · 54m

    • 72Part 1-EDA-Audio Classification Project Using Deep Learning26m
    • 73Part 2-Data Preprocessing-Audio Classification Project Using Deep Learning18m
    • 74Part 3-Model Creation-Audio Classification Project Using Deep Learning10m

  2. Day 30 · 26m

    • 75Part 4-Testing ANN Model-Audio Classification Project Using Deep Learning9m
    • 76Gradio Library-Interfaces for your Machine Learning Models9m
    • 77Comparing Transfer Learning Models Using Gradio8m

  3. Day 31 · 55m

    • 78TFOD 2.0 Custom Object Detection Step By Step Tutorial47m
    • 79Text Generation with Transformers (GPT-2) In 10 Lines Of Code8m

  4. Day 32 · 50m

    • 80Image Segmentation And Object Detection Using 5 Lines Of Code Using PixelLib9m
    • 81Real Time Image Segmentation And Object Detection From Live Video Stream Using PixelLib9m
    • 82Face Detection, Face Mesh, OpenPose, Holisitic, Hand Detection Using MediaPipe On Live Stream Video11m
    • 83GauGAN AI Art Tool By Nvidia- Convert Imagination Into Real Picture- Application Of GAN6m
    • 84Implementation Of Perceptron In Deep Learning Using Python From Scratch- Part 1- Ft: Sunny15m

  5. Day 33 · 1h 3m

    • 85Complete Implementation Of Perceptron In Deep Learning Using Python From Scratch1h 3m

  6. Day 34 · 32m

    • 86How to Install Ubuntu in Windows 10 with WSL2-Windows Subsystem for Linux12m
    • 87Tutorial on Automated Machine Learning using MLBox11m
    • 88Monte Carlo DropOut Layers In Deep Learning9m

Tips for finishing

  • Do the numbered tutorials first, then choose the projects that match your interests.
  • Live sessions run long; the planner gives them their own days so they don't crowd out shorter lessons.

Frequently asked questions

How long does it take to finish Krish Naik's Complete Deep Learning Playlist?

The playlist has 88 videos and 30.4 hours of content. At 1 hour a day that's about 31 days at normal speed, or 21 days at 1.5x. At 2 hours a day it's about 16 days.

More study plans

See all 166 study plans

Tools for any playlist