This project aims to introduce the concept of Deel Q Learning and use it to solve the CartPole environment from the OpenAI Gym.

Keras is a deep learning API written in Python, running on top of the machine learning platform TensorFlow. It was developed with a focus on enabling fast experimentation.

I chose Keras because Keras adopts the principle of progressive disclosure of complexity: simple workflows should be quick and easy. In contrast, arbitrarily advanced workflows should be possible via a clear path that builds upon what you’ve already learned.

final look :

I also upload the deploying process in youtube :

--

--

I will train a fully-connected neural network to image classification of dandelions and grasses. I will be using the TensorFlow Deep Learning Framework to create a neural network and training/validation dataset.

https://github.com/titax137/repo-orbit-tita/blob/head/Flower_classification_Fully_Connected_Image_Classifier.ipynb

Conclusion:

  1. The Neural Network model using CNN has a higher accuracy rate of 0.6688, while the previous neural network model has a lower accuracy level of 0.611.
  2. The Neural Network model using CNN has a lower failure rate of 0.5915, while the previous Neural Network model has a higher failure rate of 0.824

--

--