Introduction to Deep Learning and Machine Learning.pptx
- 1. Introduction to Deep Learning
- 2. Introduction to Deep learning • https://www.youtube.com/watch?v=6M5VXKL f4D4
- 3. Definition of Deep Learning • The definition of Deep learning is that it is the branch of machine learning that is based on artificial neural network architecture. An artificial neural network or ANN uses layers of interconnected nodes called neurons that work together to process and learn from the input data.
- 4. Applications of Deep Learning • Health care – MRI imaging and x-rays (cancer detection, pneumonia), Drug discovery, • Autonomous vehicles • e-commerce • Personal assistant/Voice Controlled Assistance • Automatic Image Caption Generation • Automatic Machine Translation • Image Coloring • Fraud Detection • etc • https://www.youtube.com/watch?v=1LxmmF88fDw
- 5. 5 CS 404/504, Fall 2021 ML vs. Deep Learning • Deep learning (DL) is a machine learning subfield that uses multiple layers for learning data representations ▪ DL is exceptionally effective at learning patterns Introduction to Deep Learning Picture from: https://www.xenonstack.com/blog/static/public/uploads/media/machine-learning-vs-deep-learning.png
- 6. 6 CS 404/504, Fall 2021 ML vs. Deep Learning • DL applies a multi-layer process for learning rich hierarchical features (i.e., data representations) ▪ Input image pixels → Edges → Textures → Parts → Objects Introduction to Deep Learning Low-Level Features Mid-Level Features Output High-Level Features Trainable Classifier Slide credit: Param Vir Singh – Deep Learning
- 7. 7 CS 404/504, Fall 2021 Why is DL Useful? • DL provides a flexible, learnable framework for representing visual, text, linguistic information ▪ Can learn in supervised and unsupervised manner • DL represents an effective end-to-end learning system • Requires large amounts of training data • Since about 2010, DL has outperformed other ML techniques ▪ First in vision and speech, then NLP, and other applications Introduction to Deep Learning
- 8. 8 CS 404/504, Fall 2021 Elements of Neural Networks • A neural network playground link Introduction to Neural Networks
- 9. 9 CS 404/504, Fall 2021 Generalization • Underfitting ▪ The model is too “simple” to represent all the relevant class characteristics ▪ E.g., model with too few parameters ▪ Produces high error on the training set and high error on the validation set • Overfitting ▪ The model is too “complex” and fits irrelevant characteristics (noise) in the data ▪ E.g., model with too many parameters ▪ Produces low error on the training error and high error on the validation set Generalization
- 10. 10 CS 404/504, Fall 2021 Overfitting • Overfitting – a model with high capacity fits the noise in the data instead of the underlying relationship Generalization Picture from: http://cs231n.github.io/assets/nn1/layer_sizes.jpeg • The model may fit the training data very well, but fails to generalize to new examples (test or validation data)