Taechno
The AI Race -
Documentary ABC TV
Нейронные сети
за 30 минут:
от теории до практики.
Мозг изменяющий себя сам.
Нейропластичность Мозга .
Часть 1.
Обучение свёрточных нейронных сетей
(демо)
CBC, Anna Marie Tromanti:
Interview with Google's AI
and Deep Learning Godfather
Geoffrey Hinton
(深度学习)?
Why need
the feature normalization
(deep learning)?
Capsuls-O-Rama
AND
World of Neural Nets
Ciao Capsuls!
November 10, 2017
On July 6th, 2017, Guy Reading published his conversation with Eric Schmidt, the executive Chairman of Alphabet, Google's parent company in the website called "LEARNERBY.COM" which was entitled "Artificial Intelligence and the Fourth Industrial Revolution."
Mr. Schmidt in this conversation with Mr. Reading said that Artificial Intelligence (AI) can be applied to any complex system — including those involved in cyber-war or other military applications. It took over a decade for people to understand the ethical effects of nuclear weapons, and there will be a similar process for AI.[1]
In response to a question in the conversation, "How do you think AI can improve our lives?" Mr. Schmidt stated that today, we're at a point where computer vision is better than human vision, and language translation is nearing equivalence with human ability. Vision, text, images and speech are all essentially at human levels.[1]
In this conversation, Mr. Reading asked "what areas could AI potentially be used for the detriment of society?" Mr. Schmidt answered Machine learning is applicable to any form of large, complex network. As one more positive example — we have the world's most efficient data centres. [1]
什么是卷积神经网络 CNN (深度学习)?
What is
Convolutional Neural Networks
(deep learning)?
[ИТ лекторий]:
Семинар
по глубокому обучению
или как стать
Data Scientist’ом
Как устроены искусственные
нейронные сети?
— Научпок
Как обучить нейронную сеть?
Как применяются нейросети
в быту?
Mr . Schmidt added, "We had incredibly smart folks working on tuning and designing data centres to achieve that efficiency. When we used the algorithm I mentioned to you, TensorFlow, we saw a fifteen percent improvement over the best human tuner. This was seriously humbling for those Google people — the engineers who built the AI system are incredibly proud of themselves." [1]
The executive Chairman of Alphabet, Google's parent company continued: "However, AI could be applied to automated systems involved in cyber war. It's not clear to me whether that gives one side an advantage, but it's something we have to think about." [1]
Mr. Schmidt also addressed, "“What we don't have is the next layer of cognition. Machine learning can achieve some aspects of that, but AI is really about imagining systems that seem to have some aspects of intelligence.”[1]
On November 3, 2017, Robby Berman, published an article in a website called "BiGTHINK.COM" which was entitled "Buh-Bye, ‘Traditional’ Neural Networks. Hello, Capsules. "[2]
Mr. Berman wrote that if you have a recent phone, odds are you have a neural net in your pocket or handbag. That’s how ubiquitous neural nets have become. They’ve got caché, and manufacturers brag about using them in everything, from voice recognition to smart thermostats to self-driving cars."[2]
The author of this article added that a search for “neural network” on Google nets nearly 35 million hits. But “traditional” neural nets may already be on their way out, thanks to Geoff Hinton of Google itself. He’s introduced something even cutting-edgier: “capsule” neural nets. [2]
Mr. Berman talked about the neural nets and explained that they are more properly referred to as “artificial neural networks,” or “ANNs for shot. (We’ll just call them “neural networks” or “nets” here.) A neural network is a classifier that can sort an object into a correct category based on input data.[2]
The author stated that the foundation of a neural network is its artificial neurons, or “ANs,” each one assigning a value to information it’s received according to some rule.[2]
Mr. Berman went further on and wrote, "Groups of ANs are arranged in layers that together come to a prediction of some sort that’s then passed on to the next layer, and so on, until understanding is achieved. In convolutional neural networks, insights travel up and down the layers, continually modifying the ANs’ rules to fix errors and deliver the most accurate outputs." [2]
The writer of the article talked about Professor Geoffrey Hinton's capsule network and says that with Hinton’s capsule network, layers are comprised not of individual ANs, but rather of small groups of ANs arranged in functional pods, or “capsules.” [2]
The author talked about each capsule in details with the following words: "Each capsule is programmed to detect a particular attribute of the object being classified, thus getting around the need for massive input data sets. This makes capsule networks a departure from the “let them teach themselves” approach of traditional neural nets."[2]
什么是神经网络 (机器学习)
what is neural network
in machine learning
Capsule Networks:
An Improvement to Convolutional Networks
Lecture 1.1 —
Why do we need machine learning
[Neural Networks
for Machine Learning]
Hinton and Capsule Networks
| AiNews 3
Mr. Berman addressed, " layer is assigned the task of verifying the presence of some characteristic, and when enough capsules are in agreement on the meaning of their input data, the layer passes on its prediction to the next layer." [2]
In his article, the writer explained to the readers that so far, capsule nets have proven equally adept at as traditional neural nets at understanding handwriting, and cut the error rate in half for identifying toy cars and trucks. Impressive, but it’s just a start.[2]
In conjunction with the current implantation of capsule networks, Mr. Berman cited Professor Hinton's argument who had stated that slower than it will have to be in the end. He’s got ideas for speeding them up, and when he does, Hinton’s capsules may well spark a major leap forward in neural networks, and in AI. [2]
Ilya Sutskever:
The Learning of Algorithms
GTC 2016:
NVIDIA DGX-1, World's First
Deep Learning Supercomputer
(part 7)
Ray Kurzweil -
Human-Level AI
is Just 12 Years Away
What is
Convolutional Neural Networks
(deep learning)?
what is neural network
in machine learning
не самые умные существа
на планете Земля
Нейронные сети:
настоящее и будущее
Is AI Riding
a One-Trick Pony
Google’s
AI Wizard Unveils
a New Twist on Neural Networks
Sara Sabour:
Dynamic Routing
Between Capsules
A capsule is a group of neurons
Understanding Dynamic Routing
between Capsules
How U of T's
'godfather' of
deep learning
is reimagining AI
Google's Hinton outlines new AI
优化器 Optimizer 加速神经网络训练 (深度学习)
Speed up neural network
training process
(deep learning)
怎样检验神经网络 (深度学习)?
How
to evaluate neural networks
(deep learning)?
Neural Network!
OCR NETWORK
Моя первая нейронная сеть!
Neural Network Simulator
Neural Network 3D Simulation
Machine Learning
for Flappy Bird
using Neural Network &
Genetic Algorithm
How
to Make a Neural Network -
Intro to Deep Learning
#2
How to Do
Mathematics Easily
- Intro to Deep Learning
#4
A friendly introduction
to Deep Learning
and Neural Networks
Deep Learning Demystified
How we teach computers
to understand pictures
| Fei Fei Li
Nuts and Bolts of
Applying Deep Learning
(Andrew Ng)
Andrew Ng, Chief Scientist
at Baidu
【三橙传媒】
创业美国第一季第三集
Coursera,揭秘谷歌最强大脑吴恩达 S1E3
百度大脑辞职！吴恩达写信赞李彦宏
聊技术，李彦宏贬低对手夸百度
除了李彦宏坐无人车上五环，
百度AI开发者大会还有哪些精彩瞬间？
2016 GTC 北京：Andrew Ng
人工智能是新生力量（七）
What is machine learning?
