In this SAS How To Tutorial, Christa Cody shows how to create machine learning models using SAS Viya. First, you will be shown a coding example in SAS of supervised learning in SAS Studio which is great for those who are familiar with SAS programming. She will then create the same model using Model Studio machine learning pipelines. This approach may be more useful for someone unfamiliar or uninterested in programming the model themselves, but still want to have similar control over hyperparameters. After watching this video and see the coding examples, you will have a better understanding of how to build machine learning models in SAS.

In my last blog I summarized a research paper that investigated the use of residual neural networks for the purposes of radio signal classification. In this blog I will get you started with Google Cloud Platform and show you how to build a ResNet signal classifier in Python with Keras. Here is a link to my GitHub with the ResNet code: GitHub. The authors of the paper include a link to the dataset that was used in the experiment so we can conduct our own experiments and training sessions. I will walk you through my experience coding a ResNet and reproducing the experiment from the paper.

Learn how to get started with robotics programming using Robot Operation System (ROS). Targeted for absolute beginners in ROS, Linux, and Python, this short guide shows you how to build your own robotics projects. ROS is an open-source and flexible framework for writing robotics software. With a hands-on approach and sample projects, Robot Operating System for Absolute Beginners will enable you to begin your first robot project. You will learn the basic concepts of working with ROS and begin coding with ROS APIs in both C and Python.

On October 10th, our team hosted a live webinar--Simple Distributed Deep Learning Model Inference--with Xiangrui Meng, Software Engineer at Databricks. Model inference, unlike model training, is usually embarrassingly parallel and hence simple to distribute. However, in practice, complex data scenarios and compute infrastructure often make this "simple" task hard to do from data source to sink. In this webinar, we provided a reference end-to-end pipeline for distributed deep learning model inference using the latest features from Apache Spark and Delta Lake. While the reference pipeline applies to various deep learning scenarios, we focused on image applications, and demonstrated specific pain points and proposed solutions.

We live in a time where we are able to monitor everything--servers, containers, fitness levels, power consumption, etc. Making predictions on time series data is often just as important as monitoring is. In this latest Data Science Central webinar, we will learn about how InfluxDB can be used with TensorFlow and FB's Prophet to make predictions and solve data engineering problems.

Many Data Scientists spend much of their time on laptops, working with familiar tools like Jupyter and Conda, on data that fits on their machine. In this latest Data Science Central webinar we will discuss a laptop-like experience for Data Science and Machine Learning, supporting the same tools and workflows you have become accustomed to. We will highlight how Databricks augments that experience with collaborative features like co-editing and commenting, as well as enterprise-level security, scalability, and reliability.

To acquire a new skill, humans learn better and faster if a tutor, based on their current knowledge level, informs them of how much attention they should pay to particular content or practice problems. Similarly, a machine learning model could potentially be trained better with a scorer that "adapts" to its current learning state and estimates the importance of each training data instance. Training such an adaptive scorer efficiently is a challenging problem; in order to precisely quantify the effect of a data instance at a given time during the training, it is typically necessary to first complete the entire training process. To efficiently optimize data usage, we propose a reinforcement learning approach called Differentiable Data Selection (DDS). In DDS, we formulate a scorer network as a learnable function of the training data, which can be efficiently updated along with the main model being trained. Specifically, DDS updates the scorer with an intuitive reward signal: it should up-weigh the data that has a similar gradient with a dev set upon which we would finally like to perform well. Without significant computing overhead, DDS delivers strong and consistent improvements over several strong baselines on two very different tasks of machine translation and image classification.

In deep reinforcement learning (RL), adversarial attacks can trick an agent into unwanted states and disrupt training. We propose a system called Robust Student-DQN (RS-DQN), which permits online robustness training alongside Q networks, while preserving competitive performance. We show that RS-DQN can be combined with (i) state-of-the-art adversarial training and (ii) provably robust training to obtain an agent that is resilient to strong attacks during training and evaluation.

Artificial intelligence is influencing the future of virtually every industry and every human being. It has acted as the main driver of emerging technologies like big data, robotics, and IoT, and it will continue to act as a technological innovator for the near future. According to tech experts, artificial intelligence (AI) has the potential to transform the world. However, those same experts do not agree on what kind of effect that transformation will have on the average person. Some believe that humans will be much better off in the hands of advanced AI systems, while others think it will lead to our inevitable downfall.

This guide shows how to install scikit-learn.