AlexNet

Use the mouse wheel or two fingers (on touchscreens) to zoom in and out of the map.

Map view:

Zoom: 100%

More settings

Connection length 100% Label size 100% Node size 100% Line width 100% Label width 100%

Export map as:

AlexNet topic overview

The analysis highlights History and Products as prominent areas in the source structure around AlexNet.

Related topics: 76
Source areas: 4
Connected nodes: 80
Extracted relationships: 67
Concept neighborhoods: 24
Bridge connections: 80

What this topic covers Research coverage

Source areas are shown by the number of related topics found in each part of the analysis. Use smaller areas too: they can reveal specialized angles and content gaps.

History · 41 topics

Overview · 12 topics

Training · 12 topics

Architecture · 11 topics

Smaller areas are not necessarily less important. They contain fewer connections in this analysis and can be useful for finding specialized angles or coverage gaps.

Key facts & relationships

High-confidence facts extracted from structured source data. Use them as anchors for further research.

Developers: Alex Krizhevsky, Ilya Sutskever, and Geoffrey Hinton
License: New BSD License
Release: September 30, 2012; 13 years ago (2012-09-30)
Repository: code.google.com/archive/p/cuda-convnet/
Type: Convolutional neural network
Written in: CUDA, C++

Explore all related topics Closing gaps

Browse the complete topic structure, not only the most central items. Less prominent entities and concepts can reveal missing angles, specialized context and useful research gaps. Each item opens a new analysis centered on that subject.

Overview

Convolutional neural network
ImageNet
Alex Krizhevsky
Ilya Sutskever
Geoffrey Hinton
University of Toronto
Neurons Artificial neuron
Graphics processing units Graphics processing unit
ImageNet Large Scale Visual Recognition Challenge
Deep learning
Neural networks Neural network (machine learning)
Computer vision

Architecture

Layers Layer (deep learning)
Convolutional Convolution
Max-pooling Pooling layer
VRAM
Nvidia
GTX 580
Dropout Dropout (neural networks)
ReLU
Activation function
Tanh
Sigmoid Sigmoid function

Training

Training set
TFLOPS Floating point operations per second
Float32
Momentum gradient descent
Data augmentation
Whitens Whitening transformation
Principal directions Principal component analysis
Local response normalization
Weights were initialized Weight initialization
Gaussians Normal distribution
Dying ReLU
Ensemble Ensemble learning

History

Kunihiko Fukushima
Neocognitron
Unsupervised learning
LeNet-5 LeNet
Yann LeCun
Backpropagation
Max pooling
GPGPU General-purpose computing on graphics processing units
Deep belief network
GTX 280
IDSIA
State of the art
Databases Database
CUDA
GPU
Kernel regression
Support vector machines Support vector machine
AdaBoost
Feature engineering
SIFT Scale-invariant feature transform
SURF Speeded up robust features
HoG Histogram of oriented gradients
Bags of visual words Bag-of-words model in computer vision
Jitendra Malik
Fei-Fei Li
Amazon Mechanical Turk
WordNet
CIFAR-10
Hyperparameter optimization
European Conference on Computer Vision
GPU computing
Google Scholar
GoogLeNet Inception (deep learning architecture)
VGGNet
Highway network
ResNet Residual neural network
SqueezeNet
MobileNet
EfficientNet
BSD-2 license BSD licenses
Computer History Museum

Advanced semantic analysis

Deeper signals for content research, entity SEO and topical coverage. The plain-language headings explain what each technical view is useful for.

How AlexNet connects Entity context

The extracted context around AlexNet shows recurring relationship patterns in the source. For example, AlexNet → Based, CPUs, Each, GFLOPs, GPU, GPUs, JPEG, Nvidia GTX, RAM, TFLOPS, The, The GPUs, The ImageNet, These GPUs, They, US Another extracted example is AlexNet → AdaBoost, During, For, Geoffrey Hinton, Hinton, HoG, ImageNet, In, It, Jitendra Malik, Malik, PASCAL Visual Object Classes, SIFT, SURF, What. Use these groups to spot repeated connection types before inspecting the individual relationships.

Top relations

related to Training · 16

AlexNet → Based, CPUs, Each, GFLOPs, GPU, GPUs, JPEG, Nvidia GTX, RAM, TFLOPS, The, The GPUs, The ImageNet, These GPUs, They, US

related to Computer vision · 15

AlexNet → AdaBoost, During, For, Geoffrey Hinton, Hinton, HoG, ImageNet, In, It, Jitendra Malik, Malik, PASCAL Visual Object Classes, SIFT, SURF, What

related to ImageNet competition · 9

AlexNet → AlexNets, CONV, ILSVRC-2012, ImageNet, ImageNet Fall, Specifically, The, These, They

related to Previous work · 8

AlexNet → CNN, Cresceptron, In, It, Kunihiko Fukushima, Max, The LeNet-5, Yann LeCun

related to Subsequent work · 8

AlexNet → As, At, BSD, CNNs, Google Scholar, GPU-based, GPUs, The

related to Architecture · 4

AlexNet → GPU, Nvidia GTX, The, VRAM

Developers · 1

AlexNet → Alex Krizhevsky, Ilya Sutskever, and Geoffrey Hinton

License · 1

AlexNet → New BSD License

Release · 1

AlexNet → September 30, 2012; 13 years ago (2012-09-30)

Repository · 1

AlexNet → code.google.com/archive/p/cuda-convnet/

Important terminology

Use these terms to understand the vocabulary surrounding the topic, not as a checklist for keyword stuffing.

Important terminology

imagenet training network trained neural deep visual gpu 2012 convolutional krizhevsky images recognition computer hinton image first learning performance large

AlexNet relationships Subject–Predicate–Object triples

TTTA extracted 67 structured relationships around AlexNet. Examples in this analysis include AlexNet → Developers → Alex Krizhevsky, Ilya Sutskever, and Geoffrey Hinton and AlexNet → License → New BSD License. The table shows each extracted connection, where it came from and its confidence.

Subject	Predicate	Object	Confidence	Src
AlexNet	Developers	Alex Krizhevsky, Ilya Sutskever, and Geoffrey Hinton	1.00	infobox
AlexNet	License	New BSD License	1.00	infobox
AlexNet	Release	September 30, 2012; 13 years ago (2012-09-30)	1.00	infobox
AlexNet	Repository	code.google.com/archive/p/cuda-convnet/	1.00	infobox
AlexNet	Type	Convolutional neural network	1.00	infobox
AlexNet	Written in	CUDA, C++	1.00	infobox
AlexNet	is a	convolutional neural network architecture developed for image classification tasks	0.90	text
AlexNet	related to Architecture	The	0.60	section
AlexNet	related to Architecture	GPU	0.60	section
AlexNet	related to Architecture	VRAM	0.60	section
AlexNet	related to Architecture	Nvidia GTX	0.60	section
AlexNet	related to Computer vision	During	0.60	section

Related concept clusters Concept neighborhoods

The concept neighborhoods around AlexNet bring nearby vocabulary together. In this analysis, examples include Trained, Computer and Scale. Use the clusters to find adjacent concepts and terminology that may deserve separate research.

AlexNet
- Trained
- Computer
- Scale
- Architecture
- Subsequent
- Performance
- Recognition
- Vision
- Imagenet
- Visual
- Neural
- Network
alexnet
- Trained
- Computer
- Scale
- Architecture
- Subsequent
- Performance
- Recognition
- Vision
- Imagenet
- Visual
- Neural
- Network
convolutional neural network
- Neural
- Networks
- Gpu
- Architecture
- Subsequent
- Training
- Recognition
- First
- Visual
- Work
- Large
- Network
imagenet
- Scale
- Large
- Data
- Recognition
- First
- Hinton
- Training
- Krizhevsky
- Visual
- Deep
- Network
- Subsequent
imagenet large scale visual recognition challenge
- Recognition
- Visual
- Scale
- Challenge
- Large
- Imagenet
- Learning
- Hinton
- Convolutional
- Networks
- Deep
- Images
deep learning
- Networks
- Subsequent
- Learning
- Scale
- Work
- Vision
- Large
- Cnn
- Recognition
- Computer
- Imagenet
- Gpu
convolutional
- Architecture
- Recognition
- First
- Visual
- Neural
- Network
- Alex
- Scale
- Work
- Challenge
- Large
- Networks
deep belief network
- Neural
- Networks
- Subsequent
- Gpu
- Learning
- Training
- Work
- Large
- Cnn
- Recognition
- Vision
- Computer

Connections between topic areas Semantic bridges

For AlexNet, one of the stronger structural bridges in this analysis connects AlexNet with History. Bridges highlight paths between different parts of the map and can reveal research angles that are easy to miss in a flat list.

Min side: 3

AlexNet — History · splits 39 ⟂ 42

AlexNet — Overview · splits 68 ⟂ 13

AlexNet — Training · splits 68 ⟂ 13

AlexNet — Architecture · splits 69 ⟂ 12

Map overview Semantic statistics

AlexNet

Nodes81

Edges80

Triples67

Avg. degree1.98

Density0.024691

Components1

Source & methodology

TTTA analyzes the structure around AlexNet to surface related topics, entities, relationships, concept neighborhoods and bridge connections. Use the map to explore areas such as History & Products, including less central topics that may reveal useful research gaps. Automatically extracted connections are research leads rather than rewritten encyclopedia content.

Source: Wikipedia — AlexNet · EN edition · Analysis: TopicsToTalkAbout