Neural Networks Representation Nonlinear hypotheses Machine Learning Nonlinear
- Slides: 34
Neural Networks: Representation Non-linear hypotheses Machine Learning
Non-linear Classification x 2 x 1 size # bedrooms # floors age Andrew Ng
What is this? You see this: But the camera sees this: Andrew Ng
Computer Vision: Car detection Not a car Cars Testing: What is this? Andrew Ng
pixel 1 Learning Algorithm pixel 2 Raw image pixel 2 Cars “Non”-Cars pixel 1 Andrew Ng
pixel 1 Learning Algorithm pixel 2 Raw image pixel 2 Cars “Non”-Cars pixel 1 Andrew Ng
pixel 1 Learning Algorithm pixel 2 50 x 50 pixel images→ 2500 pixels (7500 if RGB) Raw image pixel 2 pixel 1 intensity pixel 2500 intensity Cars “Non”-Cars pixel 1 Quadratic features ( ): ≈3 million features Andrew Ng
Neural Networks: Representation Neurons and the brain Machine Learning
Neural Networks Origins: Algorithms that try to mimic the brain. Was very widely used in 80 s and early 90 s; popularity diminished in late 90 s. Recent resurgence: State-of-the-art technique for many applications Andrew Ng
The “one learning algorithm” hypothesis Auditory Cortex Auditory cortex learns to see [Roe et al. , 1992] Andrew Ng
The “one learning algorithm” hypothesis Somatosensory Cortex Somatosensory cortex learns to see [Metin & Frost, 1989] Andrew Ng
Sensor representations in the brain Seeing with your tongue Human echolocation (sonar) Haptic belt: Direction sense [Brain. Port; Welsh & Blasch, 1997; Nagel et al. , 2005; Constantine-Paton & Law, 2009] Implanting a 3 rd eye Andrew Ng
Neural Networks: Representation Model representation I Machine Learning
Neuron in the brain Andrew Ng
Neurons in the brain [Credit: US National Institutes of Health, National Institute on Aging] Andrew Ng
Neuron model: Logistic unit Sigmoid (logistic) activation function. Andrew Ng
Neural Network Layer 1 Layer 2 Layer 3 Andrew Ng
Neural Network “activation” of unit in layer matrix of weights controlling function mapping from layer to layer If network has units in layer , will be of dimension . units in layer , then Andrew Ng
Neural Networks: Representation Model representation II Machine Learning
Forward propagation: Vectorized implementation Add . Andrew Ng
Neural Network learning its own features Layer 1 Layer 2 Layer 3 Andrew Ng
Other network architectures Layer 1 Layer 2 Layer 3 Layer 4 Andrew Ng
Neural Networks: Representation Examples and intuitions I Machine Learning
Non-linear classification example: XOR/XNOR , are binary (0 or 1). x 2 x 1 Andrew Ng
Simple example: AND 1. 0 0 0 1 1 0 1 Andrew Ng
Example: OR function -10 20 20 0 0 1 1 0 1 Andrew Ng
Neural Networks: Representation Examples and intuitions II Machine Learning
Negation: 0 1 Andrew Ng
Putting it together: -30 10 -10 20 -20 20 0 0 1 1 0 1 Andrew Ng
Neural Network intuition Layer 1 Layer 2 Layer 3 Layer 4 Andrew Ng
Handwritten digit classification [Courtesy of Yann Le. Cun] Andrew Ng
Neural Networks: Representation Multi-classification Machine Learning Andrew Ng
Multiple output units: One-vs-all. Pedestrian Want Car , when pedestrian Motorcycle , when car Truck , etc. when motorcycle Andrew Ng
Multiple output units: One-vs-all. Want , when pedestrian , when car , etc. when motorcycle Training set: one of , , , pedestrian car motorcycle truck Andrew Ng
- Neural networks and learning machines 3rd edition
- Few shot learning with graph neural networks
- Neural networks and learning machines
- Meshnet: mesh neural network for 3d shape representation
- Visualizing and understanding convolutional networks
- Liran szlak
- Neural networks ib psychology
- Audio super resolution using neural networks
- Convolutional neural networks for visual recognition
- Leon gatys
- Nvdla
- Mippers
- Convolutional neural network ppt
- Pixelrnn
- Newff matlab toolbox
- Neural networks for rf and microwave design
- 11-747 neural networks for nlp
- Perceptron xor
- Csrmm
- On the computational efficiency of training neural networks
- Threshold logic unit in neural network
- Fuzzy logic lecture
- Introduction to convolutional neural networks
- Convolutional neural networks
- Deep forest: towards an alternative to deep neural networks
- Convolutional neural networks
- Neuraltools neural networks
- Rnn
- Predicting nba games using neural networks
- The wake-sleep algorithm for unsupervised neural networks
- Audio super resolution using neural networks
- Convolutional neural network alternatives
- Difference between datagram and virtual circuit approach
- Backbone networks in computer networks
- Hypotheses development