Tony Paikeday’s answer to How can I build my own artificial intelligence system?

Can I build my own artificial intelligence system? Tony Paikeday of @nvidia discusses

  • In this setting, it may be perfectly fine follow a meandering path as you piece together a system including GPU’s, drivers, libraries, and deep learning frameworks that interest you, sifting through potentially hundreds of pages of documentation, as you take on the role of “system integrator”.
  • NVIDIA DGX Systems see a 30% increase in deep learning performance compared with other systems built using the same Tesla V100 GPU’s, but lacking integrated, optimized deep learning software.
  • The important takeaway here is that, even if you build an A.I. system on your own, using the absolute latest GPU technology, that system would still be at a performance disadvantage relative to an integrated hardware and software system that’s fully-optimized and software-engineered for maximum performance of each deep learning framework.
  • Alternatively, A.I. appliances like NVIDIA’s DGX, that include access to popular deep learning frameworks like TensorFlow, Caffe2, MXNet and more, as well as supporting libraries, all integrated with the hardware, can save considerable time and money.
  • Additionally, with the experimental nature of data science and A.I., developers often find themselves (or their teams) needing to simultaneously experiment with different combinations of system resources and software configurations, in order to determine which model can derive insights fastest.

Like a lot of things, the answer is “it depends”. If we take deep learning as an example of an increasingly popular A.I. workload, building an AI system for deep learning training on your datasets is largely a function of the resources, expertise and amount of infrastructure you have readily accessible. For example, the system you might employ as an independent developer, or as a researcher in a smaller setting, would look considerably different from what you would need to support a larger organization’s efforts to “A.I.-enable” their business interactions with customers, or improve the quality of clinical care, or detect fraud in a voluminous flow of financial transaction data. Ultimately this becomes of question of whether you design and build your own system, or employ a purpose-built solution for your problem.
Continue reading “Tony Paikeday’s answer to How can I build my own artificial intelligence system?”

The AI Revolution Is Eating Software: NVIDIA Is Powering It

Find out how we're immersed in this extraordinary momentum of the #AI revolution:

  • Volta features a new numeric format and CUDA instruction that perform 4×4 matrix operations – an elemental deep learning operation – at super-high speeds

    Each Volta GPU is 120 teraflops.

  • It’s great to see the two leading teams in AI computing race while we collaborate deeply across the board – tuning TensorFlow performance, and accelerating the Google cloud with NVIDIA CUDA GPUs.
  • It provides a 5x improvement over Pascal, the current-generation NVIDIA GPU architecture, in peak teraflops, and 15x over the Maxwell architecture, launched just two years ago – well beyond what Moore’s law would have predicted.
  • Such leaps in performance have drawn innovators from every industry, with the number of startups building GPU-driven AI services growing more than 4x over the past year to 1,300.
  • To help innovators move seamlessly to cloud services such as these, at GTC we launched the NVIDIA GPU Cloud platform, which contains a registry of pre-configured and optimized stacks of every framework.

At this year’s GTC Conference, NVIDIA showed how it is delivering AI for every computing platform, every deep learning framework. Read more.
Continue reading “The AI Revolution Is Eating Software: NVIDIA Is Powering It”

First Global Credit Launches AICOIN Pre-subscription ICO – The Merkle

  • AICOIN is a passive investment vehicle that uses a strategy combining the pinpoint accuracy of Artificial Intelligence trading models with the “Wisdom of the Crowd” to generate a profit for coin holder / investors.
  • The ongoing profits generated from the AI directed trading are then fed into an Investment Pool that is used to finance positions in early stage companies focused on AI and public blockchain technology.
  • Unlike traditional VC’s and seed funds the AICoin Investment Pool is directed by AICoin token holders.
  • The power of the blockchain as a voting mechanism enables the collective to aggregate the combined knowledge and expertise from all of the token holders in a completely secure and transparent way to profit from the “Wisdom of the Crowd” to make investment decisions that benefit both the AICoin token holders and the cryptocurrency ecosystem as a whole.
  • These five opportunities are fully vetted by the investment board, consisting of two appointed seats and a seat elected by the coin holders, all of whom have years of experience in the financial markets and are leaders in their industries.

AICOIN is a passive investment vehicle that uses a strategy combining the pinpoint accuracy of Artificial Intelligence trading models with the “Wisdom of the Crowd” to generate a profit for coin holder / investors.
Continue reading “First Global Credit Launches AICOIN Pre-subscription ICO – The Merkle”

Is China in the driver’s seat when it comes to AI?

Is #China in the driver’s seat when it comes to #AI?

  • In the final months of the Obama administration, the U.S. government published two separate reports noting that the U.S. is no longer the undisputed world leader in AI innovation and expressing concern about China’s emergence as a major player in the field.
  • The reports recommended increased expenditure on machine learning research and enhanced collaboration between the U.S. government and tech industry leaders to unlock the potential of AI.
  • But despite these efforts, 91 percent of the 1,268 tech founders, CEOs, investors, and developers surveyed at the international Collision tech conference in New Orleans in May 2017 believed that the U.S. government is “fatally under-prepared” for the impact of AI on the U.S. ecosystem.
  • Research firm CB Insights found that Chinese participation in funding rounds for American startups came close to $10 billion in 2016, while recent figures indicate that Chinese companies have invested in 51 U.S. AI companies, to the tune of $700 million.
  • But of further surprise was the 50 percent of all respondents who believed the U.S. would lose its dominant position in the tech world to China within just five years.

In the battle of technological innovation between East and West, artificial intelligence (AI) is on the front line. And China’s influence is growing.
Continue reading “Is China in the driver’s seat when it comes to AI?”

How an artificial brain could help us outsmart hackers

How an artificial brain could help us to outsmart hackers

  • The big conceptual difference between deep learning and traditional machine learning is that deep learning is the first, and currently the only learning method that is capable of training directly on the raw data (e.g., the pixels in our face recognition example), without any need for feature extraction.
  • When applying traditional machine learning, it is necessary to first convert the computer files from raw bytes to a list of features (e.g., important API calls, etc), and only then is this list of features fed into the machine learning module.
  • Additionally, unlike traditional machine learning, which reaches a performance ceiling as the number of files it is trained on increases, deep learning can effectively improve as the datasets grow, to the extent of hundreds of millions of malicious and legitimate files.
  • The results of benchmarks that compare the performance of deep learning vs traditional machine learning in cybersecurity show that deep learning results in a considerably higher detection rate and a lower false positive rate.
  • As malware developers use more advanced methods to create new malware, the gap between the detection rates of deep learning vs traditional machine learning will grow wider; and in coming years it will be critical to rely on deep learning in order to have a realistic chance of foiling the most sophisticated attacks.

During the past few years, deep learning has revolutionized nearly every field it has been applied to, resulting in the greatest leap in performance in the history of computer science.
Continue reading “How an artificial brain could help us outsmart hackers”

Deep Learning Papers Reading Roadmap

#ICYMI #DeepLearning Papers Reading Roadmap

  • [pdf](ResNet,Very very deep networks, CVPR best paper)

    [8] Hinton, Geoffrey, et al. “Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups.”

  • “Speech recognition with deep recurrent neural networks.”
  • [pdf]

    [11] Sak, Haşim, et al. “Fast and accurate recurrent neural network acoustic models for speech recognition.”

  • [pdf] (Google Speech Recognition System)

    [12] Amodei, Dario, et al. “Deep speech 2: End-to-end speech recognition in english and mandarin.”

  • [pdf] (Baidu Speech Recognition System)

    After reading above papers, you will have a basic understanding of the Deep Learning history, the basic architectures of Deep Learning model(including CNN, RNN, LSTM) and how deep learning can be applied to image and speech recognition issues.


The roadmap is constructed in accordance with the following four guidelines: from outline to detail; from old to state-of-the-art; from generic to specific areas; focus on state-of-the-art.

Continue reading “Deep Learning Papers Reading Roadmap”

Learning Deep Learning with Keras

Learning #DeepLearning with #Keras  #NeuralNetworks @pmigdal

  • For that reason, I suggest starting with image recognition tasks in Keras, a popular neural network library in Python.
  • Deep learning is a name for machine learning techniques using many-layered artificial neural networks.
  • See a plot of AUC score for logistic regression, random forest and deep learning on Higgs dataset (data points are in millions):

    In general there is no guarantee that, even with a lot of data, deep learning does better than other techniques, for example tree-based such as random forest or boosted trees.

  • Deep learning (that is – neural networks with many layers) uses mostly very simple mathematical operations – just many of them.
  • Its mathematics is simple to the point that a convolutional neural network for digit recognition can be implemented in a spreadsheet (with no macros), see: Deep Spreadsheets with ExcelNet.

I teach deep learning both for a living (as the main deepsense.io instructor, in a Kaggle-winning team1) and as a part of my volunteering with the Polish Chi…
Continue reading “Learning Deep Learning with Keras”