Deep Learning

A Visual Introduction
Interest
Google NGRAM & Google Trends
Hype or Reality?
Quotes

I have worked all my life in Machine Learning, and I’ve never seen one
algorithm knock over benchmarks like Deep Learning
– Andrew Ng (Stanford & Baidu)

Deep Learning is an algorithm which has no theoretical limitations

of what it can learn; the more data you give and the more
computational time you provide, the better it is – Geoffrey Hinton (Google)

Human-level artificial intelligence has the potential to help humanity

thrive more than any invention that has come before it – Dileep George
(Co-Founder Vicarious)

For a very long time it will be a complementary tool that human

scientists and human experts can use to help them with the things
that humans are not naturally good – Demis Hassabis (Co-Founder DeepMind)
Hype or Reality?
Deep Learning at Google
Hype or Reality?
NIPS (Computational Neuroscience Conference) Growth
What is Artificial Intelligence?

Input: Output:
Artificial
Sensors Intelligence Movement
Data Text
Machine Learning - Basics
Introduction

Machine Learning is a type of Artificial Intelligence that provides

computers with the ability to learn without being explicitly
programmed.

Machine Learning
Algorithm
Labeled Data

Training
Prediction

Learned Model Prediction

Data

Provides various techniques that can learn from and make predictions on data
Machine Learning - Basics
Learning Approaches

Supervised Learning: Learning with a labeled training set

Example: email spam detector with training set of already labeled emails

Unsupervised Learning: Discovering patterns in unlabeled data

Example: cluster similar documents based on the text content

Reinforcement Learning: learning based on feedback or reward

Example: learn to play chess by winning or losing
Machine Learning - Basics
Problem Types

Classification Regression
(supervised – predictive) (supervised – predictive)

Clustering Anomaly Detection

(unsupervised – descriptive) (unsupervised– descriptive)
Machine Learning - Basics
Algorithms Comparison - Classification
What is Deep Learning?

Part of the machine learning field of learning representations of

data. Exceptional effective at learning patterns.

Utilizes learning algorithms that derive meaning out of data by using

a 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.
Inspired by the Brain

The first hierarchy of neurons

that receives information in the
visual cortex are sensitive to
specific edges while brain regions
further down the visual pipeline
are sensitive to more complex
structures such as faces.

Our brain has lots of neurons connected together and the strength of
the connections between neurons represents long term knowledge.

1 One learning algorithm hypothesis: all significant mental algorithms

are learned except for the learning and reward machinery itself.
Why Deep Learning?
Applications

Speech Computer Natural Language

Recognition Vision Processing
A brief History
A long time ago…

Convolution Neural Networks for Google Brain Project on

Handwritten Recognition 16k Cores
1958 Perceptron 1974 Backpropagation 1998 2012

awkward silence (AI Winter)

1969 1995 2006 2012

Perceptron criticized SVM reigns Restricted AlexNet wins
Boltzmann ImageNet
Machine
A brief History
The Big Bang aka “One net to rule them all”

ImageNet: The “computer vision World Cup”

A brief History
The Big Bang aka “One net to rule them all”

Deep Learning in Speech Recognition

What changed?
Old wine in new bottles

Big Data Computation Algorithmic

(Digitalization) (Moore’s Law, GPUs) Progress
The Big Players
Superstar Researchers

Geoffrey Hinton: University of Toronto & Google

Yann LeCun: New York University & Facebook

Andrew Ng: Stanford & Baidu

Yoshua Bengio: University of Montreal

Jürgen Schmidhuber: Swiss AI Lab & NNAISENSE

The Big Players
Companies
The Big Players
Startups

DNNresearch
Acquired
Deep Learning - Basics
No more feature engineering

Traditional
Feature
Learning
Engineering
Input Data Algorithm

Costs lots of time

Deep
Learning
Input Data Algorithm
Deep Learning - Basics
Architecture

A deep neural network consists of a hierarchy of layers, whereby each layer

transforms the input data into more abstract representations (e.g. edge ->
nose -> face). The output layer combines those features to make predictions.
Deep Learning - Basics
What did it learn?

Edges Nose, Eye… Faces

Deep Learning - Basics
Artificial Neural Networks

Consists of one input, one output and multiple fully-connected hidden layers in-
between. Each layer is represented as a series of neurons and progressively extracts
higher and higher-level features of the input until the final layer essentially makes a
decision about what the input shows. The more layers the network has, the higher-
level features it will learn.
Deep Learning - Basics
The Neuron

An artificial neuron contains a nonlinear activation function and has

several incoming and outgoing weighted connections.

Neurons are trained to filter and detect specific features or patterns

(e.g. edge, nose) by receiving weighted input, transforming it with
the activation function und passing it to the outgoing connections.
Deep Learning - Basics
Non-linear Activation Function

Most deep networks use ReLU -

max(0,x) - nowadays for hidden
layers, since it trains much faster, is
more expressive than logistic
function and prevents the gradient
vanishing problem.

Non-linearity is needed to learn complex (non-linear)

representations of data, otherwise the NN would be just
a linear function.
Deep Learning - Basics
The Training Process

Forward it trough
the network to get
Sample labeled data predictions

Update the Backpropagate

connection weights the errors

Learns by generating an error signal that measures the difference between the
predictions of the network and the desired values and then using this error signal
to change the weights (or parameters) so that predictions get more accurate.
Deep Learning - Basics
Gradient Descent

Gradient Descent finds the (local) the minimum of the cost function (used to
calculate the output error) and is used to adjust the weights.
Deep Learning - Basics
Data transformation in other dimensions

A neural network is transforming the data into other dimensions to solve

the specified problem.
Deep Learning - Basics
Deep Autoencoders

Composed of two symmetrical

deep-belief networks. The encoding
network learns to compresses the
input to a condensed vector
(dimensionality reduction). The
decoding network can be used to
reconstruct the data.

Topic Modeling: Document in a collection is converted to a Bag-of-

Words and transformed to a compressed feature vector using an
autoencoder. The distance from every other document-vector can be
measured and nearby document-vectors fall under the same topic.
Deep Learning - Basics
Convolutional Neural Nets (CNN)

Convolutional Neural Networks learn a complex representation of visual data

using vast amounts of data. They are inspired by the human visual system and
learn multiple layers of transformations, which are applied on top of each other
to extract a progressively more sophisticated representation of the input.

Every layer of a CNN takes a 3D volume of numbers and outputs a 3D volume of

numbers. E.g. Image is a 224*224*3 (RGB) cube and will be transformed to
1*1000 vector of probabilities.
Deep Learning - Basics
Convolutional Neural Nets (CNN)

Convolution layer is a feature detector that automagically learns to filter out not
needed information from an input by using convolution kernel.

Pooling layers compute the max or average value of a particular feature over a
region of the input data (downsizing of input images). Also helps to detect objects
in some unusual places and reduces memory size.
Deep Learning - Basics
Recurrent Neural Nets (RNN)

general computers which can learn algorithms to map input sequences to

output sequences

RNNs are general computers which can learn algorithms to map input
sequences to output sequences (flexible-sized vectors). The output
vector’s contents are influenced by the entire history of inputs.

State-of-the-art results in time series prediction, adaptive robotics,

general computers whichrecognition,
handwriting can learn image
algorithms to mapspeech
classification, input sequences
recognition, to
stock market prediction, and other sequence learning problems.
output sequences
Everything can be processed sequentially.
Deep Learning - Basics
Long Short-Term Memory RNN (LSTM)

A Long Short-Term Memory (LSTM) network is a

particular type of recurrent network that works
slightly better in practice, owing to its more
powerful update equation and some appealing
back propagation dynamics.

The LSTM units give the network memory cells with read, write
general computers which can learn algorithms to map input sequences to
and reset operations. During training, the network can learn when
output sequences
it should remember data and when it should throw it away.

Well-suited to learn from experience to classify, process

general computers which can learn algorithms to map input sequences to
and predict time series when there are very long time lags of
output sequences
unknown size between important events.
Deep Learning - Basics
Recurrent Neural Nets (RNN) – Generating Text

To train the RNN, insert characters sequentially and

predict the probabilities of the next letter.
Backpropagate error and update RNN’s weights to
increase the confidence of the correct letter (green)
and decrease the confidence of all other letters (red).

Trained on structured Wikipedia markdown. Network learns to spell English words

completely from scratch and copy general syntactic structures.
Deep Learning - Basics
Recurrent Neural Nets (RNN) – Generating Text

To generate text, we feed a character into the trained RNN and get a distribution
over what characters are likely to come next (red = likely). We sample from this
distribution, and feed it right back in to get the next letter.

This highlighted neuron gets very excited (green = excited, blue = not excited) when
the RNN is inside the [[ ]] markdown environment and turns off outside of it.

The RNN is likely using this neuron to remember if it is inside a URL or not.
Deep Learning - Basics
Image Captioning – Combining CNN and RNN

Neural Image Caption

Generator generates fitting
natural-language captions
only based on the pixels by
combining a vision CNN and
a language-generating RNN.

A close up of a child holding Two pizzas sitting on top of A man flying through the air
a stuffed animal a stove top oven while riding a skateboard
Deep Learning - Basics
Natural Language Processing – Embeddings

Embeddings are used to turn textual data (words, sentences, paragraphs) into high-
dimensional vector representations and group them together with semantically
similar data in a vectorspace. Thereby, computer can detect similarities
mathematically.
Deep Learning - Basics
Natural Language Processing – Word2Vec

Word2Vec is an unsupervised learning algorithm for obtaining vector

representations for words. These vectors were trained for a specific domain on
a very large textual data set. GloVe is a better performing alternative.

It detects similarities mathematically by grouping the vectors of similar words together.

All it needs is words co-occurance in the given corpus.
Deep Learning - Basics
Natural Language Processing – Word2Vec

Woman – Man ≈ Aunt - Uncle

King - Male + Female ≈ Queen
Human - Animal ≈ Ethics
Deep Learning - Basics
Natural Language Processing – Thought Vectors

Thought vectors is a way of embedding thoughts in vector space. Their

features will represent how each thought relates to other thoughts.

By reading every document on the web, computers might be able to

reason like humans do by mimicking the thoughts expressed in content.

A neural machine translation is trained on bilingual text

using a encoder and decoder RNN. For translation, the input
sentence is transformed into a thought vector. This vector is
used to reconstruct the given thought in another language.
Deep Learning - Basics
DeepMind Deep Q-Learning

Deep Q-Learning (DQN) is a model-free approach to reinforcement learning

using deep networks in environments with discrete action choices
Deep Learning - Basics
DeepMind Deep Q-Learning

Outperforms humans in over 30 Atari games just by receiving the pixels on the
screen with the goal to maximize the score (Reinforcement Learning)
Deep Learning - Basics
DeepMind Deep Q-Learning

Policy distillation: Extracts the learned state (policy) of a

reinforcement learning agent (teacher) and trains a new
network (student) that performs at the expert level while
being dramatically smaller and more efficient.

Single-task policy distillation Multi-task policy distillation

Deep Learning - Basics
Usage Requirements

Large data set with good quality (input-output mappings)

Measurable and describable goals (define the cost)

Enough computing power (AWS GPU Instance)

Excels in tasks where the basic unit (pixel, word) has very little meaning
in itself, but the combination of such units has a useful meaning
Deep Learning - Tools
Its all Open Source
Deep Learning - Tools
Computing is affordable

AWS EC2 GPU Spot Instance: g2.2xlarge - $0.0782 per Hour

The DIGITS DevBox combines the

world’s best hardware (4 GPUs),
software, and systems engineering
for deep learning in a powerful
solution that can fit under your
desk. Cost: $15k
Outlook
NVIDIA Pascal

NVIDIA’s Pascal GPU architecture will accelerate

deep learning applications up to 10X beyond the
speed of its current-generation Maxwell processors.
Outlook
Artificial Quantum Intelligence

Quantum Artificial Intelligence Lab is a joint initiative of NASA and Google to

study how quantum computing might advance machine learning. This type of
computing may provide the most creative and parallelized problem-solving
process under the known laws of physics.

Quantum computers handle what are called quantum bits

or qubits that can readily have a value of one or zero or
anything in between.

Quantum computing represents a paradigm shift, a radical

change in the way we do computing and at a scale that has
unimaginable power – Eric Ladizinsky (Co-founder D-Wave)
Outlook
Neuromorphic Chips

IBM TrueNorth is a brain-inspired computer chip that implements

networks of integrate-and-fire spiking artificial neurons and uses
only a tiny 70 mw of power –orders of magnitude less energy
than traditional chips. The system is designed to be able to run
deep-learning algorithms.

1 million 256 million 4096

Programmable Programmable Neurosynaptic
Neurons Synapses Cores
Outlook
Deep Learning

Significant advances in deep reinforcement and unsupervised

learning

Bigger and more complex architectures based on various

interchangeable modules/techniques

Deeper models that can learn from much fewer training cases

Harder problems such as video understanding and natural language

processing will be successfully tackled by deep learning algorithms
Takeaways

Machines that learn to represent the world from experience.

Deep Learning is no magic! Just statistics in a black box, but

exceptional effective at learning patterns.

We haven’t figured out creativity and human-empathy.

Transitioning from research to consumer products. Will make the

tools you use every day work better, faster and smarter.
Lukas Masuch
@lukasmasuch
+lukasmasuch