What Do These Terms Mean???
Deep Learning - a subset of machine learning where artificial neural networks, algorithms inspired by the human brain, learn from large amounts of data.
- Similarly to how we learn from experience, the deep learning algorithm would perform a task repeatedly, each time tweaking it a little to improve the outcome.
- We refer to ‘deep learning’ because the neural networks have various (deep) layers that enable learning.
- Just about any problem that requires “thought” to figure out is a problem deep learning can learn to solve.
PyTorch - a Python library for building deep learning models and other machine learning algorithms.
- released in early 2017
- an open source project by the Facebook AI Research team
- being adopted by teams everywhere in industry and academia
Tensor - the main data structure of PyTorch
autograd - a module that PyTorch uses to calculate gradients for training neural networks.
backpropagation - ?
- family of methods used to efficiently train artificial neural networks (ANNs) following a gradient descent approach that exploits the chain rule
gradient descent approach - ??
- an optimization algorithm used to minimize some function by iteratively moving in the direction of steepest descent as defined by the negative of the gradient
chain rule - ??
- a formula for computing the derivative of the composition of two or more functions.
transfer learning - ?
- a machine learning method where a model developed for a task is reused as the starting point for a model on a second task
Note:
? - term found in the lesson
?? - term found while researching a strange term (to me) that was found in the lesson
References:
Secure and Private AI Lesson 1 in Udacity
What is Deep Learning AI? A Simple Guide with 8 Practical Examples
Backpropagation
Gradient Descent
Chain Rule
Transfer Learning
Photo by JESHOOTS.COM on Unsplash
Comments
Post a Comment