Neural Networks
and Machine Learning
- Instructor: Prof. Emre Neftci
- UC Irvine Fall Quarter 2020
- Canvas Website
- https://nmi-lab.org/PSYCH239-NNML20/
- Print PDF (works best on Chrome/Chromium)
- Audio slideshow instructions:
- Press play on audio interface below to start the slide show
- Audio slideshow works on all platforms (Windows, Mac OX, Linux, Android) with Chrome, Chromium and Firefox. It does not work with iOS.
Example: Keyword Detection
- Every second, the microphone will collect roughly 44,000 samples. Each sample is a measurement of the amplitude of the sound wave
- How to detect "Alexa" , "OK, Google" from the raw audio?
Example: Face Detection
- Every image is a collection of numbers indicating the intensity of the color channel at a given pixel
- How to detect the presence of a face in a picture?
Machine Learning Approach
- The goal of Machine Learning (ML) is to learn to solve a problem by extracting patterns from raw data
- The performance of ML models depends heavily on the representation of the data
- Neural Networks are particularly efficient at learning these representations
History of Artificial Intelligence and Neural Networks
Early AI shortcomings:
- Symbol based processing lacks domain-specific knowledge
- Combinatorial explosion: solutions to small problems did not scale to exponentially large problems.
- Solving a problem in principle is very different than solving it practically
AI's Moonshot
Modern Artificial Intelligence and Machine Learning
A lot of progress in machine learning can be attributed to better hardware and more data
Connectionism and Neural Networks
- At the heart of deep learning, there is an artificial neural network
- Artificial neural networks are a subset of machine learning approaches using networks of simple (neuron-like) units.
Machine Learning / Artificial Intelligence
Deep learning is a kind of representation learning, which is in turn a kind of machine learning, which is used for many but not all approaches to AI"
(Goodfellow et al. 2016)
How does deep learning differ from other AI systems?
(Goodfellow et al. 2016)
Learning from Examples
- Machine learning typically uses (large) datasets to learn to
- Recognize patterns (Classification)
- Generate patterns (Generation)
- Take Actions (Reinforcement Learning)
Visual Recognition
- Visual Recognition (Image Classification) is the most common task performed by neural networks
- Neural networks are trained using a dataset consisting of pairs of images and labels
Example Dataset: MNIST and CIFAR
MNIST
CIFAR10
- MNIST/CIFAR10 are considered as the "Hello, World" example of deep learning
Example Dataset: ImageNet
- ImageNet: 1M images, 1000 classes, 469x387 pixels
Example Dataset: CelebA
- CelebA: large-scale face attributes dataset with more than 200K celebrity images, each with 40 attribute annotations.
Beyond Image Classification
Machine Learning and neural networks can be applied to a wide variety of problems, such as:
- Image Segmentation and Object Detection
- Text or Audio Classification
- Regression
- Translation
- Anomaly Detection
- Generation (Density Estimation)
Other (Non-Visual) Datasets:
- Speech Commands: 65,000 one-second long utterances of 30 short words, such as "Yes", "No", "Right", "Stop"
- Penn Tree Bank (PTB) dataset: A text corpus that is parsed and annotated for natural language processing research
- SMS Spam Collection Dataset: 5574 messages, tagged according being ham (legitimate) or spam
Convolutional Neural Networks: Image Classification
YOLO: Object Detection
U-Nets: Image Segmentation
Neural Style Transfer
Neural Style Transfer: Deep Empathy
Image Generation Using Generative Adversarial Networks (GAN)
Visual Attention: Captioning
Deep Reinforcement Learning: Game of Go
Silver, et al. 2016
Sequence Prediction
- Data can have a temporal structure
- Neural networks can be applied to learn and predict sequences
- Recurrent Neural Networks are one such example
C. Olah, 2015
Robot Control: Solving Rubik's Cube with a Robot Hand
OpenAI, 2019
WaveNets: Voice and Music Generation
- Parametric Text-To-Speech
- WaveNet
Van den Oord et al. 2016
Attention Networks: Machine Translation
Bahdenau, et al. 2015
ML/NN as Models for Understanding the Brain
Blake, et al. 2019
- ML/NN attempts to solve tasks that are similar to that of animals.
- Researchers use ML/NN to make hypotheses in the brain.
The Explosion of Deep Learning
- Deep Learning has become the de facto solution for any representation learning problem
- Neural Information Processing Systems (NeurIPS) is the most prestigious conference in ML/AI
- 13'000 Participant in 2019
- In 2018, the main conference sold out after 12 minutes
Books
- Machine Learning
- Ian Goodfellow, Yoshua Bengio, and Aaron Courville. Deep learning. MIT press, 2016.
- C.M. Bishop. Pattern recognition and machine learning. Springer-Verlag New York, Inc. Secaucus, NJ, USA, 2006.
- Biologically-Inspired Neural Networks
- Wulfram Gerstner, Werner M Kistler, Richard Naud, and Liam Paninski. Neuronal dynamics: From single neurons to networks and models of cognition. Cambridge University Press, 4.
- E. O. Neftci, H. Mostafa, and F. Zenke. “Surrogate Gradient Learning in Spiking Neural Networks: Bringing the Power of Gradient-Based Optimization to Spiking Neural Networks”. IEEE Signal Processing Magazine 36.6 (Nov. 2019), pp. 51–63.
Course Overview (Weeks 1-3)
- Historical perspective and Course logistics (Today)
- Pattern Recognition Basics (1 Week)
- Linear Regression, Classification (k-Nearest Neighbor, Perceptrons, Multilayer Perceptrons)
- Machine Learning and Deep Learning (2 Weeks)
- Software and computer setup
- Deep Neural Networks
- Loss functions
- Optimization, Gradient Backpropagation
Course Overview (Weeks 5-10)
- Applications (4 weeks)
- Visual Recognition: ConvNets
- Pattern Generation: Autoencoders, Variational Autoencoders and Generative Adversarial Networks
- Sequence Learning: Recurrent Neural Networks, LSTM, WaveNet
- Natural Language Processing: Embeddings, Transformer Networks
- From Artificial Neural Networks to Biological Neural Nets: (1 week)
- Spiking Neural Networks
- Surrogate Gradient Learning
- Final Projects Presentation (Last week)
Software and Assignments
This is a hands-on class comprising programming assignments. All programming will be browser-based (no installation necessary):
- Programming Language: Python 3
- Expected basic scientific programming skills in Python, and familiarity with the concepts in sections 1.1 through 1.4 in the scipy lecture notes.
- Programming Environment: Jupyter + Google Colaboratory
- Deep Learning Environment: PyTorch
Final Project
- Topic in ML/NN:
- Apply a neural network to a new dataset, or
- Modify an algorithm on an existing dataset
- Week 10: 10+5 min presentation
- Finals Week: Project report, using NeurIPS conference paper template https://nips.cc/Conferences/2015/PaperInformation/StyleFiles
- Discuss topic with instructor before week 6
- Groups of two OK, but delineate contributions
Final Project: Example Projects
Visual / Sequence Recognition
- Terrain Classification from Videos
- Agent Localization using Video
Computational Neuroscience
- Representation Similarity Analysis with Binary Neural Networks
Classification/Regression on neuroimaging data
- Artifact detection using EEG
- Representation Similarity Analysis using Convnets and behavioral and neuroimaging data
If possible, choose a topic that relates to your expertise and research
Neural Networks and Machine Learning Instructor: Prof. Emre Neftci UC Irvine Fall Quarter 2020 Canvas Website https://nmi-lab.org/PSYCH239-NNML20/ Print PDF (works best on Chrome/Chromium) Audio slideshow instructions: Press play on audio interface below to start the slide show Audio slideshow works on all platforms (Windows, Mac OX, Linux, Android) with Chrome, Chromium and Firefox. It does not work with iOS.