What deep learning is good for
- **Problems with long lists of rules****一when the traditional approach fails, machine learning/deep learning may help.
- **Continually changing environments****一deep learning canadapt (‘learn’) to new scenarios.
- **Discovering insights within large collections of data****一can you imagine trying to hand-craft rules for what 101 different kinds of food look like?
What deep learning is not good for
- When you need explainability一the patterns learned by a deep learning model are typically uninterpretable by a human.
- When the traditional approach is a better option一if you can accomplish what you need with a simple rule-based system.
- When errors are unacceptable一since the outputs of deeplearning model aren’t always predictable.
- When you don’t have much data一deep learning models usually require a fairly large amount of data to produce great resulits.
Machine Learning VS. Deep Learning
Machine learning(more suited for structured data):
- Random forest
- Gradient boosted models
- Naive Bayes
- Nearest neighbour
- Support vector machine
- …many more
Deep learning(more suited for unstructured data):
- Neural networks
- Fully connected neural network
- Convolutional neural network
- Recurrent neuralnetwork
- Transtormer
- …many more
What are neural networks?
Types of Learning
- Supervised Learning
- Unsupervised & Self -supervised Learning
- Transfer Learning
What is deep learning actually used for?
- Recommendation
- Translation, Speech recognition
- Computer Vision, NLP
What is the pytorch
- Most popular research deep learning framework
- Write fast deep learning code in Python (able to run on a GPU/many GPUs)
- Able to access many pre-built deep learning models(Torch Hub, torchvision.models)
- Whole stack: preprocess data, model data, deploy model in your application/cloud
- Originally designed and Used in-house by Facebook/Meta (now open- source and Used by companies SUch as Tesla, Microsoft, OpenAl)
What is a tensor？
Go google hahahaha