Collaborating Authors


AWAC: Accelerating online reinforcement learning with offline datasets


Robots trained with reinforcement learning (RL) have the potential to be used across a huge variety of challenging real world problems. To apply RL to a new problem, you typically set up the environment, define a reward function, and train the robot to solve the task by allowing it to explore the new environment from scratch. While this may eventually work, these "online" RL methods are data hungry and repeating this data inefficient process for every new problem makes it difficult to apply online RL to real world robotics problems. What if instead of repeating the data collection and learning process from scratch every time, we were able to reuse data across multiple problems or experiments? By doing so, we could greatly reduce the burden of data collection with every new problem that is encountered.

Language-Generating A.I. Is a Free Speech Nightmare


"What in the name of Paypal and/or Palantir did you just say about me, you filthy degenerate? I'll have you know I'm the Crown Prince of Silicon Valley, and I've been involved in numerous successful tech startups, and I have over $1B in liquid funds. I've used that money to promote heterodox positions on human enhancement, control political arenas, and am experimenting with mind uploading. I'm also trained in classical philosophy and was recently ranked the most influential libertarian in the world by Google. You are nothing to me but just another alternative future. I will wipe you out with a precision of simulation the likes of which has never been seen before, mark my words."

TensorFlow - Azure Databricks


To make sure that your experiment logs are reliably stored, Azure Databricks recommends writing logs to DBFS (that is, a log directory under /dbfs/) rather than on the ephemeral cluster file system. For each experiment, start TensorBoard in a unique directory. For each run of your machine learning code in the experiment that generates logs, set the TensorBoard callback or filewriter to write to a subdirectory of the experiment directory. That way, the data in the TensorBoard UI will be separated into runs.

Google's 'Lip Synch' Challenge To Teach Its AI Systems How We Speak


The Lip Synch challenge, recently introduced by Google's AI Experiment group, aims at teaching the tech giant's AI system the art of reading lips. This initiative is being executed to help Google develop applications for people with speaking disabilities, such as Amyotrophic lateral sclerosis (ALS). Google plans to take assistance from professional singers to help their AI systems learn the skill of synchronisation. The platform is very self-descriptively named Lip Synch and is built by YouTube for Chrome on desktop. Lip Sync offers participants to sing a particular segment of the "Dance Monkey" by Tones and I, the only permissible sound bite accepted currently.

Artificial Intelligence Enhances Speed of Discoveries For Particle Physics


Researchers at MIT have recently demonstrated that utilizing artificial intelligence to simulate aspects of particles and nuclear physics theories can lead to faster algorithms, and therefore faster discoveries when it comes to theoretical physics. The MIT research team combined theoretical physics with AI models to accelerate the creation of samples that simulate interactions between neutrons, protons, and nuclei. There are four fundamental forces that govern the universe: gravity, electromagnetism, the weak force, and the strong force. The strong, weak, and electromagnetic forces are studied through particle physics. The traditional method of studying particle interactions requires running numerical simulations of these interactions between particles, typically taking place at 1/10th or 1/100th the size of a proton.

Rethinking The Way We Benchmark Machine Learning Models


"Unless you have confidence in the ruler's reliability, if you use a ruler to measure a table, you may also be using the table to measure the ruler." Do machine learning researchers solve something huge every time they hit the benchmark? If not, then why do we have these benchmarks? But, if the benchmark is breached every couple of months then research objectives might become more about chasing benchmarks than solving bigger problems. In order to address these challenges, researchers at Facebook AI have introduced Dynabench, a new platform for dynamic data collection and benchmarking.

Focal Loss in Object Detection


So Focal Loss reduces the loss contribution from easy examples and increases the importance of correcting misclassified examples.) So, let's first understand what Cross-Entropy loss for binary classification. The idea behind Cross-Entropy loss is to penalize the wrong predictions more than to reward the right predictions.

Introducing Our Low Code Machine Learning Platform


We are very excited to release the free tier of dunnhumby Model Lab this as part of our partnership with Microsoft. We make it easy to connect your data, clean your data, and run your machine learning pipeline within minutes. You can then take that output and copy right into a notebook for further refinement if needed. You can create new projects, reference datasets, and create multiple experiments in just a few clicks! You can also follow the progress of your machine learning experiments as they update in real-time.

The use of graph neural networks to discover particles


Machine learning algorithms can beat the world's hardest video games in minutes and solve complex equations faster than the collective efforts of generations of physicists. But the conventional algorithms still struggle to pick out stop signs on a busy street. Object identification continues to hamper the field of machine learning--especially when the pictures are multidimensional and complicated, like the ones particle detectors take of collisions in high-energy physics experiments. However, a new class of neural networks is helping these models boost their pattern recognition abilities, and the technology may soon be implemented in particle physics experiments to optimize data analysis. This summer, Fermilab physicists made an advance in their effort to embed graph neural networks into the experimental systems.

'Attacking at speed': Army Project Convergence and breakthrough lightning-fast war

FOX News

Fox News Flash top entertainment and celebrity headlines are here. Check out what's clicking today in entertainment. The U.S. military recently conducted a live-fire full combat replication with unmanned-to-unmanned teaming guiding attacks, small reconnaissance drones, satellites sending target coordinates to ground artillery and high-speed, AI-enabled "networked" warfare. This exercise was a part of the Army's Project Convergence 2020, a weapons and platform combat experiment which, service leaders say, represents a massive transformation helping the service pivot its weapons use, tactics and maneuver strategies into a new era. Taking place at Yuma Proving Grounds, Arizona, Project Convergence involved live-fire war experiments aligned in three distinct phases, intended to help the Army cultivate its emerging modern Combined Arms Maneuver strategy.