Machine Learning Model Optimization with Hyper Parameter Tuning Approach

Abstract

Hyper-parameters tuning is a key step to find the optimal machine learning parameters. Determining the best hyper-parameters takes a good deal of time, especially when the objective functions are costly to determine, or a large number of parameters are required to be tuned. In contrast to the conventional machine learning algorithms, Neural Network requires tuning hyperparameters more because it has to process a lot of parameters together, and depending on the fine tuning, the accuracy of the model can be varied in between 25%-90%. A few of the most effective techniques for tuning hyper-parameters in the Deep learning methods are: Grid search, Random forest, Bayesian optimization, etc. Every method has some advantages and disadvantages over others. For example: Grid search has proven to be an effective technique to tune hyper-parameters, along with drawbacks like trying too many combinations, and performing poorly when it is required to tune many parameters at a time. In our work, we will determine, show and analyze the efficiencies of a real-world synthetic polymer dataset for different parameters and tuning methods.