deep learning

Neural network training

Deep learning is a branch of machine learning that uses neural networks with many layers to process data.

The "deep" refers to the number of layers through which data passes, each extracting progressively more abstract features.

Deep learning powers image recognition, language translation, and voice assistants: The model uses deep learning to identify faces in photos.

training

backpropagation

Reverse gradient computation method

convergence · momentum · checkpointing · fine-tuning · pretraining · warmup · scheduler

challenges

overfitting

Excess adaptation to samples

dropout · generalization · hyperparameters

architecture

neural networks

Layered computational learning systems

feedforward · recurrent · perceptron · BERT · GPT

applications

computer vision

AI interpreting visual data

self-driving cars · AlphaGo · facial recognition · medical imaging · text generation · drug discovery · protein folding · deepfakes

frameworks

TensorFlow

Machine learning computation library

  • GPUVisual processing hardware
Categories
Opposites
computational approach

deep learningexpert systems

AI using encoded rules

feature engineering · decision trees

model complexity

deep learninglinear regression

Statistical straight-line fitting method

decision trees

intelligence type

deep learninghuman intelligence

Innate mental capacity

human cognition · gut instinct · general intelligence

Family

deep, learning, deeply, deepest, deeper, deepening, deepened, deepness

Familiarity
Top 200,000
Profile
Used worldwide · Timeless · Abstract · Rated G