Administrative Stuff

Pre-Requisites

• Linear Algebra
• Calculus
• Probability and Statistics
• Fundamentals of Machine Learning
• Programming Experience in Python

Websites

• Course Schedule and Lecture Slides


• Use Google Classroom
• questions, discussions, announcements, homework submissions


• Linked to Google Drive through MSU

Communication

• All communication through Google Classroom
• Do NOT send emails to instructor
• HW/Exam submitted via email will NOT be graded
• Install Google Classroom App on phone, tablet, etc.
• Turn-on notification for Google Classroom
• Your responsibility to check Google Classroom regularly

Computational Resources

• MSU HPCC
• 4hr time limit on jobs
• Google Colab
• 12hr time limit on jobs
• GPU/TPU
• Personal/Lab Computers

Assignments

• Written Homeworks
• Short homeworks, 2-4 questions
• Couple of hours worth of work
• Programming Assignments
• a lot of programming
• hours and hours of programming
• days and days of debugging

Assignments and Grading

• Four Written Homeworks: 25%
• Four Programming Assignments: 50%
• Final Exam: 25%

Assignments and Grading

• Written Homeworks: top two at 7.5% and other two at 5%
• Programming Assignments: top two at 15% and other two at 10%
• Generous grading policy (grad school)
• Getting an A vs mastering the material
• Build your CV
• Take advantage of extra credit

Late Days

• 10% reduction of points per late day.
• 5 free late days total (not per assignment)
• use them wisely . . . save them for assignments towards the end

Book (Optional)

Machine Learning and Neural Networks

What is Machine Learning?

• For many problems, programing desired behavior by hand is difficult
• recognizing people and objects
• understanding human speech from audio files
• Machine learning approach: program an algorithm to automatically learn from data, or from experience
• Some reasons you might want to use a learning algorithm:
• hard to code up a solution by hand (e.g. vision, NLP)
• system needs to adapt to a changing environment (e.g. spam detection)
• want the system to perform better than the human programmers
• privacy/fairness (e.g. ranking search results)

Types of Machine Learning?

• Supervised Learning: have labeled examples of the correct behavior, i.e. ground truth input/output response
• Unsupervised Learning: no labeled examples – instead, looking for interesting patterns in the data
• Reinforcement Learning: earning system receives a reward signal, tries to learn to maximize the reward signal

What are Neural Networks?

• Most of the biological details aren’t essential, so we use vastly simplified models of neurons.


• While neural nets originally drew inspiration from the brain, nowadays we mostly think about math, statistics, etc.


• Neural networks are collections of thousands (or millions) of these simple processing units that together perform useful computations.

What are Neural Networks?

But why neural networks?

• Hypothesis: Most processing in the brain may be due to a single learning algorithm.


• Premise: Most of human intelligence may be due to a single learning algorithm.


• Conclusion: Build learning algorithms that mimic the brain.

But Why Neural Networks Now?

• Inspiration from the brain
• proof of concept that a neural architecture can see and hear!
• Very effective across a range of applications (vision, text, speech, medicine, robotics, etc.)
• Widely used in both academia and the tech industry
• Powerful software frameworks (PyTorch, TensorFlow, etc.) let us quickly implement sophisticated algorithms
• Current parlance: Deep Learning
• Emphasizes that the algorithms often involve hierarchies with many stages of processing

Deep Learning

Deep Learning: Where does it fit?

Deep Learning=Learning Representation/Features

• Traditional model of pattern recognition: fixed/hand-engineered features + trainable classifier

• End-to-End learning/feature learning/deep learning: trainable features + trainable classifier

Architectures for Pattern Recognition

• Classical architectures for pattern recognition: Speech Recognition

• Classical architectures for pattern recognition: Image Recognition

Deep Learning = Learning Hierarchical Representations

• Deep Architecture: more than one stage of non-linear feature extraction

Trainable Feature Hierarchies: End-to-End Learning

• A hierarchy of trainable feature transforms
• Each module transforms its input representation into a higher-level representation.
• High-level features are more global and more invariant
• Low-level features are shared among categories
• Deep Learning Goal: Make all modules trainable and get them to learn appropriate representations.

Deep Learning

• Deep Learning: many layers (stages) of processing.
• For e.g., this network recognizes objects in images,
• Each box consists of many neuron-like units.

Deep Learning

• You can visualize what a learned feature is responding to by finding an image that excites it. (We’ll see how to do this.)
• Higher layers in the network often learn higher-level, more interpretable representations

Distributed Representations

What is a representation?

• Your data representation determines what questions are easy to answer.
• A dictionary of word counts is good for questions like "What is the most common word in Hamlet?"
• It is not so good for semantic questions like "If Alice liked Harry Potter, will she like The Hunger Games?"

What is a representation?

What is a representation?

• Mathematical relationships between vectors encode the semantic relationships between words
• Measure semantic similarity using dot products
• Represent a web page with the average of its word vectors
• Complete analogies by doing arithmetic on word vectors
• "Paris is to France, as London is to ________"
• Paris - France + London = ________
• Designing such representations by hand is hard, so we learn from data
• This is a big part of what neural nets do, whether it is supervised, unsupervised, or reinforcement learning!

Applications of Deep Learning

Supervised Learning Examples

• Supervised learning: have labeled examples of the correct behavior
• E.g., handwritten digit classification with the MNIST dataset
• Task: given an image of a handwritten digit, predict the digit class
• Input: the image
• Target: the digit class
• Data: 70,000 images of handwritten digits labeled by humans
• Training set: first 60,000 images, used to train the network
• Test set: last 10,000 images, not available during training, used to evaluate performance
• Neural nets already achieved $>$ 99% accuracy in the 1990s, but we still continue to learn a lot from it

Supervised Learning Examples

Supervised Learning Examples

• Object Recognition

• ImageNet dataset: 1000 categories, millions of labeled images
• Lots of variability in viewpoint, lighting, etc.
• Error rate dropped from 26% to under 4% over just a few years!

Supervised Learning Examples

Supervised Learning Examples

Unsupervised Learning Examples

• In generative modeling, we want to learn a distribution over some dataset, such as natural images.
• We can evaluate a generative model by sampling from the model and seeing if it looks like the data.

Unsupervised Learning Examples

• The progress of generative models:

• Big GAN, Brock et al, 2019:

Unsupervised Learning Examples

• Generative models of text. The models like BERT, GPT-3 perform unsupervised learning by reconstructing the next words in a sentence. The GPT-3 models learns from 499 Billion Tokens and has 175 Billion parameters.

Unsupervised Learning Examples

• Recent exciting result: a model called the CycleGAN takes lots of images of one category (e.g., horses) and lots of images of another category (e.g., zebras) and learns to translate between them.

Reinforcement Learning

• An agent interacts with an environment (e.g., game of Breakout)

• In each time step,
• The agent periodically receives a reward (e.g., points)
• agent receives observations (e.g., pixels) which give it information about the state (e.g., positions of ball and paddle)
• agent picks an action (e.g., keystrokes) that affects the state
• The agent wants to learn a policy, or mapping from observations to actions, which maximizes its average reward over time.

Reinforcement Learning

Reinforcement Learning for Control

Software and This Course

Software Frameworks

• Scientific computing (NumPy)
• vectorize computations (express them in terms of matrix/vector operations) to exploit hardware efficiency
• Neural network frameworks: PyTorch, TensorFlow, JAX, etc.
• automatic differentiation
• compiling computation graphs
• braries of algorithms and network primitives
• support for graphics processing units (GPUs)
• For this course:
• PyTorch, a widely used neural net framework with a built-in automatic differentiation feature

Software Frameworks

• Why take this class, if PyTorch does so much for you?
• So you know what to do if something goes wrong !!
• Debugging learning algorithms requires sophisticated detective work, which requires understanding what goes on beneath the hood.
• That is why we derive things by hand in this class !!