About
Description: This course provides a comprehensive introduction to artificial intelligence (AI) using Python. Participants will explore the history and evolution of neural networks, understand the differences between biological and artificial neurons, and learn the architecture and working mechanisms of artificial neural networks (ANN). The course covers essential functions such as activation, softmax, forward propagation, and loss functions. Utilizing powerful frameworks like Keras and TensorFlow 2.0, students will gain hands-on experience building and training neural networks. Practical tasks on the MNIST dataset using Jupyter Notebook will solidify their understanding. Additionally, the course delves into advanced techniques, model evaluation, and deployment using Flask or Streamlit, preparing participants to apply AI in real-world scenarios. Prerequisites • Basic understanding of Python programming. • Familiarity with basic mathematical concepts (algebra, calculus, and statistics). • Basic knowledge of machine learning concepts. Outcomes • Understand the history and evolution of neural networks. • Differentiate between biological and artificial neurons. • Comprehend the architecture and working mechanisms of artificial neural networks (ANN). • Implement various functions such as activation, softmax, forward propagation, and loss functions. • Utilize the Keras framework for building and training neural networks. • Apply backpropagation and gradient descent techniques. • Work with TensorFlow 2.0 for machine learning tasks. • Perform practical tasks on the MNIST dataset using Jupyter Notebook. • Optimize and evaluate model performance. • Deploy machine learning models using Flask or Streamlit.
You can also join this program via the mobile app. Go to the app