Learning Path for Deep Learning

If there is one area in data science which has led to the growth of Machine Learning and Artificial Intelligence in the last few years, it is Deep Learning. From research labs in universities with low success in industry to powering every smart device on the planet – Deep Learning and Neural Networks have started a revolution.

Expected Effort: 10-12 hours per week

Deep learning is ubiquitous – whether it’s Computer Vision applications or breakthroughs in the field of Natural Language Processing, we are living in a deep learning-fueled world.

  • January: Getting Started With Deep Learning and Refresher to Python/ Statistics
    • Overview of the learning path
    • Getting started with Deep Learning
    • Setting up the system
    • Descriptive Statistics & Probability
    • Getting Started With Python
  • February: Understanding Inferential Statistics & Basics Of Machine Learning
    • Inferential Statistics
    • Partial Derivative
    • Linear Algebra - Part 1 (Intro To Matrix & Vectors)
    • Linear Regression
    • Logistic Regression
    • Regularization Techniques (Ridge & Lasso)
    • Project on Classification

    Start engaging in Data Science/Deep Learning Communities

  • March: Introduction To Deep Learning and Keras
    • Linear Algebra - Part 2 (Matrix Multiplication & Inverse Of a matrix)
    • Understanding Neural Networks (MLP)
    • Build your first Neural Network in Numpy
    • Frameworks For Deep Learning
    • Intro To Keras
    • Build Neural Network in Keras
    • Project on Classification Using Deep Learning

    Start Building Your Github Profile

  • April: Improving Your Neural Network
    • Handling/ Pre-Processing Images
    • Regularization Techniques
    • Hyperparameter Tuning
    • Transfer Learning
    • Data Augmentation
    • Project 1 on Computer Vision
  • May: Understanding Convolutional Neural Network
    • Understanding CNN
    • Hyperparameter Tuning
    • Project 2 on Computer Vision

    Participate In Competition

  • June : Debugging Your Deep Learning Model
    • Visualizing Deep Learning Model
    • Project 3 on Computer Vision
    • Project 4 on Computer Vision
  • July : Sequence Models
    • Sequence Models (RNN, LSTM, GRU)
    • Handling/ Pre-Processing Text Data
    • Project 1 on NLP

    • Write Blogs
  • August : Word Embeddings
    • Word Embeddings
    • Project 2 on NLP
  • September : Attention Models
    • Attention Models
    • Project On Multi-Model Task
  • October: Unsupervised Deep Learning
    • Unsupervised Deep Learning (Autoencoders)
    • Project On Unsupervised Deep Learning
  • November: GANS
    • GANS
    • Projects On GANS
  • December: Way Forward
    • Up Level your Data Science Resume Course
    • Ace Data Science Interview Course

You might also enjoy