Redes Neuronales | 🇬🇧 Neural Networks

S++: A Fast and Deployable Secure-Computation Framework for Privacy-Preserving Neural Network Training

S++: A Fast and Deployable Secure-Computation Framework for Privacy-Preserving Neural Network Training

We introduce S++, a simple, robust, and deployable framework for training a neural network (NN) using private data from multiple sources, using secret-shared secure function evaluation. In short, consider a virtual third party to whom every data-holder sends their inputs, and which computes the neural network: in our case, this virtual third party is actually a set of servers which individually learn nothing, even with a malicious (but non-colluding) adversary.

Yann LeCun’s Deep Learning Course at CDS

Yann LeCun’s Deep Learning Course at CDS

This course concerns the latest techniques in deep learning and representation learning, focusing on supervised and unsupervised deep learning, embedding methods, metric learning, convolutional and recurrent nets, with applications to computer vision, natural language understanding, and speech recognition. The prerequisites include: DS-GA 1001 Intro to Data Science or a graduate-level machine learning course.

Introduction to CNTK Succinctly (Microsoft Cognitive Toolkit)

“Microsoft CNTK (Cognitive Toolkit, formerly Computational Network Toolkit), an open source code framework, enables you to create feed-forward neural network time series prediction systems, convolutional neural network image classifiers, and other deep learning systems. In Introduction to CNTK Succinctly, author James McCaffrey offers instruction on the basics of installing and running CNTK, and also addresses machine-learning regression and classification techniques. Exercises and explanations are included in each chapter”. (Syncfusion)

Neural Networks with JavaScript Succinctly

Although most concepts are relatively simple, there are many of them, and they interact with each other in unobvious ways, which is a major challenge of neural networks. But you can learn all important neural network concepts by running and examining the code in this book, with complete example programs for the three major types of neural network problems.

Neuronas artificiales de silicio

Neuronas artificiales en chips de silicio

El equipo de investigación dirigido por la Universidad de Bath y que incluye investigadores de las universidades de Bristol, Zurich y Auckland describió unas neuronas artificiales en un estudio publicado en la revista “Nature”. Sus usos obvios inmediatos son en casos de lesión espinal o en enfermedades degenerativas como el Alzheimer.

Células y proteínas: el modelo SNARE-CNN (red neuronal convolucional 2D)

Usando el modelo, en sus conclusiones, los autores señalan que las nuevas proteínas SNARE pueden identificarse con precisión y usarse para el desarrollo de fármacos. Y tratándose de enfermedades como las neurodegenerativas, mentales y el cáncer podemos y debemos interesarnos por este trabajo aplicado al campo de la bioinformática computacional, la minería de datos y el Machine Learning.