Great youtube series going from the basics to more complex topics of Deep Learning.
Key Points
ANNs, CNNs, Training and testing NNs, Overfitting a Neural Network, Supervised Learning
Machine learning is the practice of using algorithms to analyze data, learn from the data, then make a determination or prediction about the new data.
Different from regular coding/algorithms: focus on the learning part. Not manually writing the code. Ex. positive or negative social media. Traditional algorithmic approach: Give it positive and negative words. Machine learning approach: the algorithm analyzes large amounts of media and learn features of negative and positive
Deep Learning: subfield of machine learning that uses algorithms which mimic the structure and function of brain neural networks
Supervised learning: deep learning model that has labeled data
Artificial neural networks(ANNs): networks based on structure and function of the brain’s neural networks
Networks are based on connected units called artificial neurons, each connection between neurons can transmit a signal from one neuron to another, receiving neuron processes the signal and signals downstream neurons connected to it.
Neuron Layers: input, hidden(any inbetween), output. All input and hidden layers are dense. Each input leads to each output
Layers: each connection has a weight between 0 and 1.0
Output = activation(weighted sum of inputs) typically represent categories(cats or dogs)
Title
Deep Learning playlist overview and Machine Learning Intro
URL
https://www.youtube.com/watch?v=gZmobeGL0Yg&list=PLZbbT5o_s2xq7LwI2y8_QtvuXZedL6tQU
Summary
Great youtube series going from the basics to more complex topics of Deep Learning.
Key Points
Citation
“Deep Learning playlist overview & Machine Learning intro,” www.youtube.com. https://www.youtube.com/watch?v=gZmobeGL0Yg&list=PLZbbT5o_s2xq7LwI2y8_QtvuXZedL6tQU (accessed Feb. 15, 2023).
Repo link (optional)