Fundamentals in Neural Networks
What you'll learn
- Understand the intuition behind Artificial Neural Networks
- Understand the intuition behind Convolutional Neural Networks
- Understand the intuition behind Recurrent Neural Networks
- Apply Artificial Neural Networks in practice
- Apply Convolutional Neural Networks in practice
- Apply Recurrent Neural Networks in practice
Requirements
- There is no prior coding or programming experience required. This course assumes you have your own laptop and the code will be done using Colab.
Description
Deep learning (also known as deep structured learning) is part of a broader family of machine learning methods based on artificial neural networks with representation learning. Learning can be supervised, semi-supervised or unsupervised. Deep-learning architectures such as deep neural networks, deep belief networks, deep reinforcement learning, recurrent neural networks and convolutional neural networks have been applied to fields including computer vision, speech recognition, natural language processing, machine translation, bioinformatics, drug design, medical image analysis, material inspection and board game programs, where they have produced results comparable to and in some cases surpassing human expert performance.
This course covers the following three sections: (1) Neural Networks, (2) Convolutional Neural Networks, and (3) Recurrent Neural Networks. You will be receiving around 4 hours of materials on detailed discussion, mathematical description, and code walkthroughs of the three common families of neural networks. The descriptions of each section is summarized below.
Section 1 - Neural Network
1.1 Linear Regression
1.2 Logistic Regression
1.3 Purpose of Neural Network
1.4 Forward Propagation
1.5 Backward Propagation
1.6 Activation Function (Relu, Sigmoid, Softmax)
1.7 Cross-entropy Loss Function
1.8 Gradient Descent
Section 2 - Convolutional Neural Network
2.1 Image Data
2.2 Tensor and Matrix
2.3 Convolutional Operation
2.4 Padding
2.5 Stride
2.6 Convolution in 2D and 3D
2.7 VGG16
2.8 Residual Network
Section 3 - Recurrent Neural Network
3.1 Welcome
3.2 Why use RNN
3.3 Language Processing
3.4 Forward Propagation in RNN
3.5 Backpropagation through Time
3.6 Gated Recurrent Unit (GRU)
3.7 Long Short Term Memory (LSTM)
3.8 Bidirectional RNN (bi-RNN)
Section 4 - Technical Walkthrough: Artificial Neural Network
This section walks through each and every building block of deploying an Artificial Neural Network using tensorflow.
Section 5 - Technical Walkthrough: Convolutional Neural Network
This section walks through each and every building block of deploying a Convolutional Neural Network using tensorflow.
Section 6 - Technical Walkthrough: Recurrent Neural Network
This section walks through each and every building block of deploying an Recurrent Neural Network using tensorflow.
Section 7 - Advanced Topics: Autoencoders
This section walks through each and every building block of deploying an Autoencoder using tensorflow. Further, we explore the inference problems using the latent layers of the autoencoder.
Section 8 - Advanced Topics: Image Segmentation
This section walks through each and every building block of deploying an Image-to-image model using tensorflow.
Who this course is for:
- Beginner level audience that intends to obtain in-depth overview of Artificial Intelligence, Deep Learning, and three major types neural networks: Artificial Neural Networks, Convolutional Neural Networks, and Recurrent Neural Networks.
Instructor
I was a PhD student in Statistics at Columbia University from September of 2020 to December of 2021. I had a B.A. in Mathematics, and an M.S. in Finance from University of Rochester. I have a wide range of research interests in representation learning: Feature Learning, Deep Learning, Computer Vision (CV), and Natural Language Processing (NLP).
I am currently a Senior Data Scientist at an S&P 500 company LabCorp, developing AI-driven solutions for drug diagnostics and development. Prior, I have held professional positions such as enterprise-level Data Scientist at a EURO STOXX 50 company Bayer, quantitative researcher at AQR working on alternative quantitative strategies to portfolio management and factor-based trading, and equity trader at T3 Trading on Wall Street. I supervise a small fund specializing in algorithmic trading (since 2011, performance is here) and real estate investment. I also run my own monetarized YouTube Channel.