Data Science and Machine Learning Series: Advanced Neural Networks

English | MP4 | AVC 1280×720 | AAC 44KHz 2ch | 2h 59m | 367 MB

Master advanced neural networks and backpropagation. Follow along with machine learning expert Advait Jayant through a combination of lecture and hands-on to become competent in advanced neural network concepts, and then apply these concepts in implementing a complete neural network in Python using the pandas, numpy, Matplotlib, and Scikit-learn libraries.

The following seven topics will be covered in this Data Science and Machine Learning course:

• Introducing Neural Networks. Become competent in neural networks in this first topic in the Data Science and Machine Learning Series. Understand neurons, connections, weights, propagation functions, and learning rules. Know the difference between deep neural networks and small neural networks.
• How Neural Networks Work. Be able to explain how neural networks work in this second topic in the Data Science and Machine Learning Series. Follow along with Advait and learn about backpropagation and loss functions.
• Deriving Backpropagation in Neural Networks. Derive backpropagation in Neural Networks in this third topic in the Data Science and Machine Learning Series. Follow along with Advait and derive all of the algorithms necessary for back-propagation.
• Deriving Backpropagation using the Cross Entropy Loss Function. Derive backpropagation using the Cross Entropy Loss Function in this fourth topic in the Data Science and Machine Learning Series.
• Vectorizing Backpropagation for m-examples. Vectorize backpropagation for m-examples in this fifth topic in the Data Science and Machine Learning Series.
• The Vanishing Gradient Problem in Backpropagation. Address the Vanishing Gradient Problem in backpropagation in this sixth topic in the Data Science and Machine Learning Series. Follow along with Advait and not only understand this problem but know how to solve it.
• Implementing a 3-Layer Architecture Neural Network from Scratch. Implement a 3-layer architecture neural network from scratch in this seventh topic in the Data Science and Machine Learning Series. The three layers are input, hidden, and output. Apply the Follow along with Advait and implement a complete neural network in Python using the pandas, numpy, Matplotlib, and Scikit-learn libraries.