Autonomous car racing is a challenging task in the robotic control area. Traditional modular methods require accurate mapping, localization and planning, which makes them computationally inefficient and sensitive to environmental changes. Recently, deep-learning-based end-to-end systems have shown promising results for autonomous driving/racing. However, they are commonly implemented by supervised imitation learning (IL), which suffers from the distribution mismatch problem, or by reinforcement learning (RL), which requires a huge amount of risky interaction data. In this work, we present a general deep imitative reinforcement learning approach (DIRL), which successfully achieves agile autonomous racing using visual inputs. The driving knowledge is acquired from both IL and model-based RL, where the agent can learn from human teachers as well as perform self-improvement by safely interacting with an offline world model. We validate our algorithm both in a high-fidelity driving simulation and on a real-world 1/20-scale RC-car with limited onboard computation. The evaluation results demonstrate that our method outperforms previous IL and RL methods in terms of sample efficiency and task performance. Demonstration videos are available at https://caipeide.github.io/autorace-dirl/

Deep reinforcement learning has shown remarkable success in the past few years. Highly complex sequential decision making problems from game playing and robotics have been solved with deep model-free methods. Unfortunately, the sample complexity of model-free methods is often high. To reduce the number of environment samples, model-based reinforcement learning creates an explicit model of the environment dynamics. Achieving high model accuracy is a challenge in high-dimensional problems. In recent years, a diverse landscape of model-based methods has been introduced to improve model accuracy, using methods such as uncertainty modeling, model-predictive control, latent models, and end-to-end learning and planning. Some of these methods succeed in achieving high accuracy at low sample complexity, most do so either in a robotics or in a games context. In this paper, we survey these methods; we explain in detail how they work and what their strengths and weaknesses are. We conclude with a research agenda for future work to make the methods more robust and more widely applicable to other applications.

At a very basic level, deep learning is a machine learning technique. It teaches a computer to filter inputs through layers to learn how to predict and classify information. Observations can be in the form of images, text, or sound. The inspiration for deep learning is the way that the human brain filters information. Its purpose is to mimic how the human brain works to create some real magic. In the human brain, there are about 100 billion neurons. Each neuron connects to about 100,000 of its neighbors.

These are exciting times for the artificial intelligence community. Interest in the field is growing at an accelerating pace, registration at academic and professional machine learning courses is soaring, attendance in AI conferences is at an all-time high, and AI algorithms have become a vital component of many applications we use every day. But as with any field going through the hype cycle, AI is surrounded by a saturation of information, much of which is misleading or of little value. I can tell that from my inbox. Every day, I receive several pitches that claim company X has solved problem Y with "advanced AI techniques," or that AI can now solve problem Z. A few years ago, I might have opened and read these emails with interest.

Join live for the final day of Transform 2021, including the AI Innovation & Women in AI Awards. OpenAI has disbanded its robotics team after years of research into machines that can learn to perform tasks like solving a Rubik's Cube. Company cofounder Wojciech Zaremba quietly revealed on a podcast hosted by startup Weights & Biases that OpenAI has shifted its focus to other domains, where data is more readily available. "So it turns out that we can make a gigantic progress whenever we have access to data, and all our machine learning, unsupervised, and reinforcement learning -- they work extremely well, and there [are] actually plenty of domains that are very, very rich with data. And ultimately that was holding us back in terms of robotics," Zaremba said.

With the rising availability of computation in everyday devices, there has been a corresponding increase in the appetite for voice as the primary interface. To accomodate this desire it is necessary for us to have high quality libraries for being able to process and generate audio data that can make sense of human speech. To facilitate research and industry applications for speech data Mirco Ravanelli and Peter Plantinga are building SpeechBrain. In this episode they explain how it works under the hood, the projects that they are using it for, and how you can get started with it today. Do you want to try out some of the tools and applications that you heard about on Podcast.__init__?

Deep learning has yielded some fantastic results for basic natural language processing (NLP) functions such as named entity recognition (NER), document classification and sentiment analysis -- not to mention the abilities to generate everything from believable short stories to HTML code with minimal text inputs or prompts. In addition, deep learning can also have a dramatic impact on F1 scores, which are used as a performance measure for precision and recall, and so vendors have started to throw much of their weight and resources behind what they see as a game-changing technology. But as the CEO of a company that's been doing NLP for well over 15 years, I don't believe that deep learning is always the answer -- especially from an economic standpoint. I've watched as many new players have stepped up to the plate with NLP solutions underpinned by deep learning. But what I'm not seeing is evidence of big commercial wins, and I suspect that the cost of using deep learning-backed NLP is wiping out significant dollar gains.

The new open-source IBM Cloud-Native Toolkit is the focus of this week's automation tales. This solution is for individuals who want to integrate and execute AI and machine learning technologies in cloud environments. Codex, a deep learning model that generates software source code, has been revealed by OpenAI. One of the most compelling reasons to adopt a public workspace is to improve developer onboarding by shortening the time to first call (TTFC), the most essential measure for a public API. While Elon Musk's brain-chip company messes around with gaming monkeys, another group of researchers has achieved a major milestone in neuroprosthetics: allowing a man who can't talk to form sentences with his mind.

This is arguably the most important architecture for natural language processing (NLP) today. Specifically, we look at modeling frameworks such as the generative pretrained transformer (GPT), bidirectional encoder representations from transformers (BERT) and multilingual BERT (mBERT). These methods employ neural networks with more parameters than most deep convolutional and recurrent neural network models. Despite the larger size, they've exploded in popularity because they scale comparatively more effectively on parallel computing architecture. This enables even larger and more sophisticated models to be developed in practice. Until the arrival of the transformer, the dominant NLP models relied on recurrent and convolutional components. Additionally, the best sequence modeling and transduction problems, such as machine translation, rely on an encoder-decoder architecture with an attention mechanism to detect which parts of the input influence each part of the output. The transformer aims to replace the recurrent and convolutional components entirely with attention.

Wildfires are more and more present in modern society, mainly caused by heat waves, lightning, droughts, climate change, or even human actions like car fires and cigarette butts. We've seen it everywhere recently Brazil, Australia, United States, Canada, etc., destroying plant, human, and animal life, property damage, and contributing to global warming through the high amount of CO2 produced. These countries all have walls of videos like the one below in the county's fire emergency to see if something is going on. The most common problem is that they are spotted too late and already widely spread out. This is because you cannot have somebody staring at that wall all day, waiting to spot smoke or fire.