Auto Added by WPeMatico
TensorFlow 2.1, released last week, allows for mixed-precision training, making use of the Tensor Cores available in the most recent NVidia GPUs. In this post, we report first experimental results and provide some background on what this is all about.
First experiments with TensorFlow mixed-precision training Read More »
Broadcasting, as done by Python’s scientific computing library NumPy, involves dynamically extending shapes so that arrays of different sizes may be passed to operations that expect conformity – such as adding or multiplying elementwise. In NumPy, the way broadcasting works is specified exactly; the same rules apply to TensorFlow operations. For anyone who finds herself,
NumPy-style broadcasting for R TensorFlow users Read More »
The term “federated learning” was coined to describe a form of distributed model training where the data remains on client devices, i.e., is never shipped to the coordinating server. In this post, we introduce central concepts and run first experiments with TensorFlow Federated, using R.
A first look at federated learning with TensorFlow Read More »
Deep learning need not be irreconcilable with privacy protection. Federated learning enables on-device, distributed model training; encryption keeps model and gradient updates private; differential privacy prevents the training data from leaking. As of today, private and secure deep learning is an emerging technology. In this post, we introduce Syft, an open-source framework that integrates with
Towards privacy: Encrypted deep learning with Syft and Keras Read More »
Compared to other applications, deep learning models might not seem too likely as victims of privacy attacks. However, methods exist to determine whether an entity was used in the training set (an adversarial attack called member inference), and techniques subsumed under “model inversion” allow to reconstruct raw data input given just model output (and sometimes,
Hacking deep learning: model inversion attack by example Read More »
In this post we use tfprobability, the R interface to TensorFlow Probability, to model censored data. Again, the exposition is inspired by the treatment of this topic in Richard McElreath’s Statistical Rethinking. Instead of cute cats though, we model immaterial entities from the cold world of technology: This post explores durations of CRAN package checks,
Modeling censored data with tfprobability Read More »
PixelCNN is a deep learning architecture – or bundle of architectures – designed to generate highly realistic-looking images. To use it, no reverse-engineering of arXiv papers or search for reference implementations is required: TensorFlow Probability and its R wrapper, tfprobability, now include a PixelCNN distribution that can be used to train a straightforwardly-defined neural network
Easy PixelCNN with tfprobability Read More »
In image segmentation, every pixel of an image is assigned a class. Depending on the application, classes could be different cell types; or the task could be binary, as in “cancer cell yes or no?”. Area of application notwithstanding, the established neural network architecture of choice is U-Net. In this post, we show how to
Image segmentation with U-Net Read More »
In nonlinear dynamics, when the state space is thought to be multidimensional but all we have for data is just a univariate time series, one may attempt to reconstruct the true space via delay coordinate embeddings. However, it is not clear a priori how to choose dimensionality and time lag of the reconstruction space. In
Deep attractors: Where deep learning meets chaos Read More »
Have you ever wondered why you can call TensorFlow – mostly known as a Python framework – from R? If not – that’s how it should be, as the R packages keras and tensorflow aim to make this process as transparent as possible to the user. But for them to be those helpful genies, someone
So, how come we can use TensorFlow from R? Read More »
