Deep learning
9 likes11,882 views
Deep learning is a type of machine learning that uses neural networks inspired by the human brain. It has been successfully applied to problems like image recognition, speech recognition, and natural language processing. Deep learning requires large datasets, clear goals, computing power, and neural network architectures. Popular deep learning models include convolutional neural networks and recurrent neural networks. Researchers like Geoffry Hinton and companies like Google have advanced the field through innovations that have won image recognition challenges. Deep learning will continue solving harder artificial intelligence problems by learning from massive amounts of data.
Deep learning
- 2. Google NGRAM
- 5. What is Artificial Intelligence? • Artificial Narrow Intelligence (ANI): Machine intelligence that equals or exceeds human intelligence or efficiency at a specific task. • Artificial General Intelligence (AGI): A machine with the ability to apply intelligence to any problem, rather than just one specific problem (human-level intelligence). • Artificial Super Intelligence (ASI): An intellect that is much smarter than the best human brains in practically every field, including scientific creativity, general wisdom and social skills
- 6. Machine Learning • Machine Learning is a type of Artificial Intelligence that provides computers with the ability to learn
- 7. What is Deep Learning? • Part of the machine learning field of learning representations of data. • hierarchy of multiple layers that mimic the neural networks of our brain • If you provide the system tons of information, it begins to understand it and respond in useful ways.
- 8. Why we needs Deep Learning? • SuperIntelligent Devices • Best Solution for – image recognition – speech recognition – natural language processing – Big Data
- 10. Superstar Researchers Geoffrey Hinton: University of Toronto & Google Yann LeCun: New York University & Facebook Andrew Ng: Stanford & Baidu Yoshua Bengio: University of Montreal
- 12. Deep Learning
- 13. Deep Learning Requirements • Large data set with good quality • Measurable and describable goals • Enough computing power • Neural Network (Brain of Human)
- 14. Deep Learning Architectures Deep neural networks Deep belief networks Convolutional neural networks Deep Boltzmann machines Deep stacking networks
- 15. Artificial Neural Networks Axon Terminal Branches of Axon Dendrites S x1 x2 w1 w2 wn xn x3 w3
- 16. Activation Functions Hyperbolic Tangent Sigmoid Rectified Linear Units ReLU
- 17. ReLU • The advantages of using Rectified Linear Units in neural networks are – ReLU doesn't face gradient vanishing problem as with sigmoid and tanh function. – It has been shown that deep networks can be trained efficiently using ReLU even without pre- training.
- 20. CNN Layers • Convolution Layer • Pooling Layer • Fully-connected layer
- 22. Pooling Layer
- 23. Max Pooling
- 25. Case studies LeNet :The first successful applications of CNN AlexNet: The first work that popularized CNN in Computer Vision ZF Net: The ILSVRC 2013 winner GoogLeNet: The ILSVRC 2014 winner VGGNet: The runner-up in ILSVRC 2014 ResNet: The winner of ILSVRC 2015
- 26. AlexNet
- 29. ILSVRC • The ImageNet Large Scale Visual Recognition Challenge (ILSVRC) evaluates algorithms for object detection and image classification at large scale.
- 30. ILSVRC 2014
- 31. Datasets Benchmark MNIST Handwritten digits – 60000 Training + 10000 Test Data Google House Numbers from street view - 600,000 digit images CIFAR-10 60000 32x32 colour images in 10 classes IMAGENET >150 GB Tiny Images 80 Million tiny images Flickr Data 100 Million Yahoo dataset
- 32. MNIST Dataset
- 33. CIFAR-10 Dataset
- 34. Arabic Handwritten Digits Database • By Sherif Abdelazeem, Ezzat El-Sherif • 70,000 digits
- 35. Summary • Deep learning is a class of machine learning algorithms. • Harder problems such as video understanding , natural language processing and Big data will be successfully tackled by deep learning algorithms.