sxsw

20
hello, world EKR Everything you need to know to survive the upcoming robot apocalypse! What is Articial Intelligence? DRAFT

Upload: christopher-friel

Post on 18-Aug-2015

52 views

Category:

Engineering


1 download

TRANSCRIPT

hello, world

EKR

Everything you need to know to survive the

upcoming robot apocalypse!

What is Artificial Intelligence?

DRAFT

With artificial intelligence we are summoning the demon

Elon Musk CEO & CTO, SpaceX CEO, Tesla Motors Chairman, Solar CityDRAFT

The development of full artificial intelligence could spell the end of the human race

Stephen Hawking CH CBE FRS FRSA Director of Research, Center for Theoretical Cosmology, CambridgeDRAFT

1+1 = ?A. 0 B. 1 C. 2 D. None of the AboveDRAFT

1+1 = ?A. 0 B. 1 C. 2 D. None of the AboveDRAFT

2*2 = ?A. 2 B. 22 C. 4 D. A and BDRAFT

2*2 = ?A. 2 B. 22 C. 4 D. A and BDRAFT

Where is the maximum of this function?

A.

B.

C.

D.

x

y

DRAFT

Where is the maximum of this function?

A.

B.

C.

D.

x

y

DRAFT

x00

x01

x02

y00Σ φ

DRAFT

x00

x02

x01

Σ φ y00

y01

Σ φ

Σ φ

Σ φ

Σ φ

Σ φ

DRAFT

x00

x02

x01

Σ φ y00

y01

Σ φ

Σ φ

Σ φ

Σ φ

Σ φ

Feed-forward PassDRAFT

x00

x02

x01

Σ φ y00

y01

Σ φ

Σ φ

Σ φ

Σ φ

Σ φ

Backpropagation PassDRAFT

CNNConvolutional

Neural Network

RNNRecurrent Neural

Network

L-STMLong Short-Term

Memory

Q

DQNDeep Q-Network

C

NTM

MR

W

Neural Turing Machine

DRAFT

Going deeper with ConvolutionsGoogle used a new variant of convolutional neural network called “Inception” for classification, and for detection the R-CNN [5] was used. The results and the approach that Google’s team took are summarized here [2, 3]. Google’s team was able to train a much smaller neural network and obtained much better results compared to results obtained with convolutional neural networks in the previous year’s challenges.

1: Computers can recognize objects

DRAFT

Show and Tell: A Neural Image Caption GeneratorAutomatically describing the content of an image is a fundamental problem in artificial intelligence that connects computer vision and natural language processing. In this paper, we present a generative model based on a deep recurrent architecture that combines recent advances in computer vision and machine translation and that can be used to generate natural sentences describing an image.

2: Computers can write image captions

DRAFT

Human-level control through deep reinforcement learningWe tested this agent on the challenging domain of classic Atari 2600 games. We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to surpass the performance of all previous algorithms and achieve a level comparable to that of a professional human games tester across a set of 49 games, using the same algorithm, network architecture and hyperparameters.

3: Computers can play video games

DRAFT

4: Computers can evolve better models

Mar I/O: Evolving Neural Networks through Augmenting TopologiesNeural networks can be combined with other machine learning techniques to solve complex problems like model selection. Mar I/O is a program made of neural networks and genetic algorithms that kicks butt at Super Mario World.

DRAFT

• 2880 CUDA Cores

• 7.1 Billion Transistors

• 15 SMX units

• > 1 TFLOP FP64

• 1.5M L2 Cache

• 384-bit DDR5

GK110 / GTX Titan X, 980, …

DRAFT

DRAFT