Daily Archives: March 22, 2019
Bringing the power of AI to the Internet of Things
The Internet of Things is getting smarter. Companies are incorporating artificial intelligence—in particular, machine learning—into their IoT applications. The key: finding insights in data.
With a wave of investment, a raft of new products, and a rising tide of enterprise deployments, artificial intelligence is making a splash in the Internet of Things (IoT). Companies crafting an IoT strategy, evaluating a potential new IoT project, or seeking to get more value from an existing IoT deployment may want to explore a role for AI. Read More
AI in IoT: 4 Examples on How to Make Use of It
Technologies like Internet of Things (IoT) and Artificial Intelligence (AI) tell us that the future is now. Remarkably, these technology concepts perfectly complement each other. The number of connected devices will only expand and the mass of data produced by them will grow to head-spinning volumes. AI can help organizations gain meaningful insights from big data that IoT provides. But how do you get the insights? Has anyone already made use of AI in IoT? Let’s take a look. Read More
Combining AI, ML and IoT will establish one complete, interdependent distributed ecosystem.
With a clear blueprint to tap on the tremendous potential India holds as a digitally-enabled smart nation, Ravinder Pal Singh, Director, Digital Cities & Mega Projects, Government Segment, Dell EMC Commercial believes in India’s shinning story. Talking to Manali Jaggi of BW SmartCities, Singh elaborates on the company’s collaboration with the Government under its Smart Cities Mission and the need for a solid digital foundation to unlock the true potential of technologies like IQT, IoT, AI and ML through proper planning and execution. Read More
Artificial Intelligence And IP (Part I)
AI today is pretty incredible and prevalent in everyday interactions, from using Apple’s Siri as a personal assistant to interacting with Amazon’s Alexa at home to using chatbots on social media. As better algorithms are developed, broader data sets are provided for training, these systems continue to learn, and we have improved outputs. In 2016, for example, “The Next Rembrandt” project produced an impressive “new Rembrandt” painting more than 400 years after the master artist died. While the creators of the project acknowledge that the computer-created Rembrandt wouldn’t fool an art expert, it is still a remarkable display of machine-learning and output. As AI improves to the point where it can create art works, write newspaper articles, create new songs, or produce full-length movie scripts and novels, a number of intellectual property questions arise. Read More
Incremental Convolutional Neural Network Training
Experimenting novel ideas on deep convolutional neural networks (DCNNs) with big datasets is hampered by the fact that network training requires huge computational resources in the terms of CPU and GPU power and hours. One option is to downscale the problem, e.g., less classes and less samples, but this is undesirable with DCNNs whose performance is largely data-dependent. In this work, we take an alternative route and downscale the networks and input images. For example, the ImageNet problem of 1,000 classes and 1,2M training images can be solved in hours on a commodity laptop without GPU by downscaling images and the network to the resolution of 8 8. We attempt to provide the solution to transfer the knowledge (parameters) of a trained DCNN with lower resolution to improve the efficiency of training a DCNN with higher resolution, and continue training incrementally until the full resolution is achieved. In our experiments, this approach achieves clear boost in computing time without the loss of performance. Read More
Fully Homomorphic Encryption for Classification in Machine Learning
Using fully homomorphic encryption scheme, we construct fully homomorphic encryption scheme FHE4GT that can homomorphically compute an encryption of the greaterthan bit that indicates 𝑥 > 𝑥 ′ or not, given two ciphertexts 𝑐 and 𝑐 ′ of 𝑥 and 𝑥 ′, respectively, without knowing the secret key. Then, we construct homomorphic classifier homClassify that can homomorphically classify a given encrypted data without decrypting it, using machine learned parameters. Read More
Crypto-nets: Neural Networks over encrypted data
The problem we address is the following: how can a user employ a predictive model that is held by a third party, without compromising private information. For example, a hospital may wish to use a cloud service to predict the readmission risk of a patient. However, due to regulations, the patient’s medical files cannot be revealed. The goal is to make an inference using the model, without jeopardizing the accuracy of the prediction or the privacy of the data.
To achieve high accuracy, we use neural networks, which have been shown to outperform other learning models for many tasks. To achieve the privacy requirements, we use homomorphic encryption in the following protocol: the data owner encrypts the data and sends the ciphertexts to the third party to obtain a prediction from a trained model. The model operates on these ciphertexts and sends back the encrypted prediction. In this protocol, not only the data remains private, even the values predicted are available only to the data owner.
Using homomorphic encryption and modifications to the activation functions and training algorithms of neural networks, we present crypto-nets and prove that they can be constructed and may be feasible. This method paves the way to build a secure cloud-based neural network prediction services without invading users’ privacy. Read More
Conditionals in Homomorphic Encryption and Machine Learning Applications
Homomorphic encryption has the purpose to allow computations on encrypted data, without the need for decryption other than that of the final result. This could provide an elegant solution to the problem of privacy preservation in data-based applications, such as those provided and/or facilitated by machine learning techniques, but several limitations and open issues hamper the fulfillment of this plan. In this work we assess the possibility for homomorphic encryption to fully implement its program without the need to rely on other techniques, such as multiparty computation, which may be impossible in many actual use cases (for instance due to the high level of communication required). We proceed in two steps: i) on the basis of the well-known structured program theorem [28] we identify the relevant minimal set of operations homomorphic encryption must be able to perform to implement any algorithm; and ii) we analyse the possibility to solve -and propose an implementation for- the most fundamentally relevant issue as it emerges from our analysis, that is, the implementation of conditionals (which in turn require comparison and selection/jump operations) in full homomorphic encryption. We show how this issue has a serious impact and clashes with the fundamental requirements of homomorphic encryption. This could represent a drawback for its use as a complete solution in data analysis applications, in particular machine learning. It will thus possibly require a deep re-thinking of the homomorphic encryption program for privacy preservation. Read More
A review of homomorphic encryption and software tools for encrypted statistical machine learning
Recent advances in cryptography promise to enable secure statistical computation on encrypted data, whereby a limited set of operations can be carried out with out the need to first decrypt. We review these homomorphic encryption schemes in a manner accessible to statisticians and machine learners, focusing on pertinent limitations inherent in the current state of the art. These limitations restrict the kind of statistics and machine learning algorithms which can be implemented and we review those which have been successfully applied in the literature. Finally, we document a high performance R package implementing a recent homomorphic scheme in a general framework. Read More
Rick's Cafe AI 