A Review of Hyperparameter Tuning Techniques for Neural Networks

Curious about deep learning? Start with the Fundamentals of Deep Learning booklet to learn the essentials in 25 pages - https://misraturp.gumroad.com/l/fdl

👇 Watch my full course on deep learning on YouTube
   • 50 Days of Deep Learning  

Let's look into the commonly used hyperparameter tuning techniques for Neural Networks in this video.

We will look into Grid search, Random search, Manually zooming in and some other sophisticated techniques such as Bayesian search, gradient-based search and evolutionary algorithms.

Here are the libraries that implement some of these techniques:
Hyperopt - https://hyperopt.github.io/hyperopt/
Keras tuner - https://keras.io/keras_tuner/
Scikit-optimize - https://scikit-optimize.github.io/sta...
Sklearn-Deap - https://github.com/rsteca/sklearn-deap
Hyperband - https://github.com/zygmuntz/hyperband

RESOURCES:
Data Science Kick-starter mini-course: https://www.misraturp.com/courses/dat...
Pandas cheat sheet: https://misraturp.gumroad.com/l/pandascs
Streamlit template: https://misraturp.gumroad.com/l/stemp
NNs hyperparameters cheat sheet: https://www.misraturp.com/nn-hyperpar...
Fundamentals of Deep Learning in 25 pages: https://misraturp.gumroad.com/l/fdl

COURSES:
Hands-on Data Science: Complete your first portfolio project: https://www.misraturp.com/hods

Website - https://misraturp.com/
Twitter -   / misraturp