The past few years have witnessed breakthroughs in reinforcement learning (RL). From the first successful use of RL by a deep learning model for learning a policy from pixel input in 2013 to the OpenAI Dexterity program in 2019, we live in an exciting moment in RL research. Consequently, we need, as RL researchers, to create more and more complex environments and Unity helps us to do that. Unity ML-Agents toolkit is a new plugin based on the game engine Unity that allows us to use the Unity Game Engine as an environment builder to train agents. From playing football, learning to walk, to jump big walls, to train a cute doggy to catch sticks, Unity ML-Agents Toolkit provides a ton of amazing pre-made environment.

The Artificial Intelligence (AI) sector is rapidly growing with algorithms developing to meet and even exceed human capabilities. One awesome example is Deep Learning (DL), and emerging machine learning subfield which can continue to evolve on its own, without the need for continued programming. When companies want to use AI to expand and to get their startup to take off, one aspect is essential: the technology with which they choose to operate must be combined with an appropriate deep learning framework, particularly since each framework serves a specific purpose. In terms of smooth and quick business development, as well as efficient delivery, finding the perfect fit is not only important but also necessary. Given that deep learning is the key to performing tasks of a higher level of complexity and logical thinking, successfully building and deploying them proves to be quite a difficult challenge for data scientists and data engineers worldwide.

The world is now heading into the Fourth Industrial Revolution, as Professor Klaus Schwab, Founder and Executive Chairman of the World Economic Forum, described it in 2016. Artificial Intelligence (AI) is a key driver in this revolution and with it, machine learning is critical. But critical to the whole process is the need to process a tremendous amount of data which in turns boosts the demand for computing power exponentially. A study by OpenAI suggested that the computing power required for AI training surged by more than 300,000 times between 2012 and 2018. This represents a doubling of computing power every three months and two weeks; a number that is significantly quicker than Moore's Law which has traditionally measured the time it takes to double computing power.

State-of-the-art (SOTA) deep learning models have massive memory footprints. Many GPUs don't have enough VRAM to train them. In this post, we determine which GPUs can train state-of-the-art networks without throwing memory errors. Lambda offers GPU laptops and workstations with GPU configurations ranging from a single RTX 2070 up to 4 Quadro RTX 8000s. Additionally, we offer servers supporting up to 10 Quadro RTX 8000s or 16 Tesla V100 GPUs.

Use of deep learning in computer vision has increased in the last decade. In the past couple of years, computer vision applications such as face detection and vehicle detection have become mainstream. One of the reasons is the availability of pre-trained models. Convinced by the success of deep learning on these applications, businesses have now started to solve their own problems using deep learning. But what if the available pre-trained models are not suitable for your application?

In the past, KDnuggets has covered collections of key terms, including those for machine learning, deep learning, big data, natural language processing, and more. As we get into a new year, and as we have not published any collections of key terms in the recent past, we thought it would be a good idea to highlight some AI, data science, and machine learning terms that we should all now be familiar with in the constantly evolving landscape. As such, these terms are a combination of some more recently-emerging concepts, as well as existing concepts which may be of perceived increased importance of late. The definitions for these are a combined effort from the KDnuggets team, including Gregory Piatetsky, Asel Mendis, Matthew Dearing, and myself, Matthew Mayo. And so without any further ado, here are the first 10 terms you need to know, with the second 10 coming next week, giving us a total of 20 terms to know for 2020. Automated machine learning (AutoML) spans the fairly wide chasm of tasks which could reasonably be thought of as being included within a machine learning pipeline.

Matt Velloso, a technical advisor to Microsoft's CEO, got 24,000 likes on this tweet posted in November 2018: "Difference between machine learning and AI: If it is written in Python, it's probably machine learning. If it is written in PowerPoint, it's probably AI." This sums up the AI frenzy that has seized marketing departments and media pundits for the last three years. With the coming of age of machine learning and deep learning, many have hastily jumped to the conclusion that, at long last, humans are on the verge of creating a machine in their own image, capable of autonomous thinking--general artificial intelligence somehow emerging from more and more complex algorithms. Yes, neural networks have revolutionized the computer vision space and transformed natural language processing.

Dynamical systems can be modelled by partial differential equations and numerical computations are used everywhere in science and engineering. In this work, we investigate the performance of recurrent and convolutional deep neural network architectures to predict the surface waves. The system is governed by the Saint-Venant equations. We improve on the long-term prediction over previous methods while keeping the inference time at a fraction of numerical simulations. We also show that convolutional networks perform at least as well as recurrent networks in this task. Finally, we assess the generalisation capability of each network by extrapolating in longer time-frames and in different physical settings.

Many problems in machine learning (ML) can be cast as learning functions from sets to graphs, or more generally to hypergraphs; in short, Set2Graph functions. Examples include clustering, learning vertex and edge features on graphs, and learning triplet data in a collection. Current neural network models that approximate Set2Graph functions come from two main ML sub-fields: equivariant learning, and similarity learning. Equivariant models would be in general computationally challenging or even infeasible, while similarity learning models can be shown to have limited expressive power. In this paper we suggest a neural network model family for learning Set2Graph functions that is both practical and of maximal expressive power (universal), that is, can approximate arbitrary continuous Set2Graph functions over compact sets. Testing our models on different machine learning tasks, including an application to particle physics, we find them favorable to existing baselines.