Unlike existing robots on the market, such as Boston Dynamics' Spot, which moves around using internal maps, this robot uses cameras alone to guide its movements in the wild, says Ashish Kumar, a graduate student at UC Berkeley, who is one of the authors of a paper describing the work; it's due to be presented at the Conference on Robot Learning next month. Other attempts to use cues from cameras to guide robot movement have been limited to flat terrain, but they managed to get their robot to walk up stairs, climb on stones, and hop over gaps. The four-legged robot is first trained to move around different environments in a simulator, so it has a general idea of what walking in a park or up and down stairs is like. When it's deployed in the real world, visuals from a single camera in the front of the robot guide its movement. The robot learns to adjust its gait to navigate things like stairs and uneven ground using reinforcement learning, an AI technique that allows systems to improve through trial and error.

The very concept of teaching with deep fake technology may be unsettling to some. After all, deep fake technology, which utilizes AI and machine learning and can alter videos and animate photographs in a manner that appears realistic, has frequently been covered in a negative light. The technology can be used to violate privacy and create fake videos of real people. However, while these potential abuses of the technology are real and concerning that doesn't mean we should turn a blind eye to the technology's potential when using it responsibly, says Jaime Donally, a well-known immersive learning expert. "Typically, when we're hearing about it, it's in terms of the negative – impersonation and giving false claims," Donally says.

This course introduces you to one of the main types of Machine Learning: Unsupervised Learning. You will learn how to find insights from data sets that do not have a target or labeled variable. You will learn several clustering and dimension reduction algorithms for unsupervised learning as well as how to select the algorithm that best suits your data. The hands-on section of this course focuses on using best practices for unsupervised learning. By the end of this course you should be able to: Explain the kinds of problems suitable for Unsupervised Learning approaches Explain the curse of dimensionality, and how it makes clustering difficult with many features Describe and use common clustering and dimensionality-reduction algorithms Try clustering points where appropriate, compare the performance of per-cluster models Understand metrics relevant for characterizing clusters Who should take this course?

This specialization is intended to familiarize learners with a broad range of financial technologies. While finance has always been at the forefront of technological innovation, the financial industry is changing rapidly in the face of new technology. In the past, at the forefront of innovation in finance were central governments and financial institutions. Today, information technology firms and professionals are leading innovation in the financial industry. Our goal is to show learners the genesis and use cases of the technology.

The automatic generation of Multiple Choice Questions (MCQ) has the potential to reduce the time educators spend on student assessment significantly. However, existing evaluation metrics for MCQ generation, such as BLEU, ROUGE, and METEOR, focus on the n-gram based similarity of the generated MCQ to the gold sample in the dataset and disregard their educational value. They fail to evaluate the MCQ's ability to assess the student's knowledge of the corresponding target fact. To tackle this issue, we propose a novel automatic evaluation metric, coined Knowledge Dependent Answerability (KDA), which measures the MCQ's answerability given knowledge of the target fact. Specifically, we first show how to measure KDA based on student responses from a human survey. Then, we propose two automatic evaluation metrics, KDA_disc and KDA_cont, that approximate KDA by leveraging pre-trained language models to imitate students' problem-solving behavior. Through our human studies, we show that KDA_disc and KDA_soft have strong correlations with both (1) KDA and (2) usability in an actual classroom setting, labeled by experts. Furthermore, when combined with n-gram based similarity metrics, KDA_disc and KDA_cont are shown to have a strong predictive power for various expert-labeled MCQ quality measures.

Computing is a critical driving force in the development of human civilization. In recent years, we have witnessed the emergence of intelligent computing, a new computing paradigm that is reshaping traditional computing and promoting digital revolution in the era of big data, artificial intelligence and internet-of-things with new computing theories, architectures, methods, systems, and applications. Intelligent computing has greatly broadened the scope of computing, extending it from traditional computing on data to increasingly diverse computing paradigms such as perceptual intelligence, cognitive intelligence, autonomous intelligence, and human-computer fusion intelligence. Intelligence and computing have undergone paths of different evolution and development for a long time but have become increasingly intertwined in recent years: intelligent computing is not only intelligence-oriented but also intelligence-driven. Such cross-fertilization has prompted the emergence and rapid advancement of intelligent computing. Intelligent computing is still in its infancy and an abundance of innovations in the theories, systems, and applications of intelligent computing are expected to occur soon. We present the first comprehensive survey of literature on intelligent computing, covering its theory fundamentals, the technological fusion of intelligence and computing, important applications, challenges, and future perspectives. We believe that this survey is highly timely and will provide a comprehensive reference and cast valuable insights into intelligent computing for academic and industrial researchers and practitioners.

Reinforcement learning (RL) agents are particularly hard to train when rewards are sparse. One common solution is to use intrinsic rewards to encourage agents to explore their environment. However, recent intrinsic exploration methods often use state-based novelty measures which reward low-level exploration and may not scale to domains requiring more abstract skills. Instead, we explore natural language as a general medium for highlighting relevant abstractions in an environment. Unlike previous work, we evaluate whether language can improve over existing exploration methods by directly extending (and comparing to) competitive intrinsic exploration baselines: AMIGo (Campero et al., 2021) and NovelD (Zhang et al., 2021). These language-based variants outperform their non-linguistic forms by 47-85% across 13 challenging tasks from the MiniGrid and MiniHack environment suites.

To minimize the effect of outliers, kNN ensembles identify a set of closest observations to a new sample point to estimate its unknown class by using majority voting in the labels of the training instances in the neighbourhood. Ordinary kNN based procedures determine k closest training observations in the neighbourhood region (enclosed by a sphere) by using a distance formula. The k nearest neighbours procedure may not work in a situation where sample points in the test data follow the pattern of the nearest observations that lie on a certain path not contained in the given sphere of nearest neighbours. Furthermore, these methods combine hundreds of base kNN learners and many of them might have high classification errors thereby resulting in poor ensembles. To overcome these problems, an optimal extended neighbourhood rule based ensemble is proposed where the neighbours are determined in k steps. It starts from the first nearest sample point to the unseen observation. The second nearest data point is identified that is closest to the previously selected data point. This process is continued until the required number of the k observations are obtained. Each base model in the ensemble is constructed on a bootstrap sample in conjunction with a random subset of features. After building a sufficiently large number of base models, the optimal models are then selected based on their performance on out-of-bag (OOB) data.

We study whether language models can evaluate the validity of their own claims and predict which questions they will be able to answer correctly. We first show that larger models are well-calibrated on diverse multiple choice and true/false questions when they are provided in the right format. Thus we can approach self-evaluation on open-ended sampling tasks by asking models to first propose answers, and then to evaluate the probability "P(True)" that their answers are correct. We find encouraging performance, calibration, and scaling for P(True) on a diverse array of tasks. Performance at self-evaluation further improves when we allow models to consider many of their own samples before predicting the validity of one specific possibility. Next, we investigate whether models can be trained to predict "P(IK)", the probability that "I know" the answer to a question, without reference to any particular proposed answer. Models perform well at predicting P(IK) and partially generalize across tasks, though they struggle with calibration of P(IK) on new tasks. The predicted P(IK) probabilities also increase appropriately in the presence of relevant source materials in the context, and in the presence of hints towards the solution of mathematical word problems. We hope these observations lay the groundwork for training more honest models, and for investigating how honesty generalizes to cases where models are trained on objectives other than the imitation of human writing.

Detecting 3D objects from multi-view images is a fundamental problem in 3D computer vision. Recently, significant breakthrough has been made in multi-view 3D detection tasks. However, the unprecedented detection performance of these vision BEV (bird's-eye-view) detection models is accompanied with enormous parameters and computation, which make them unaffordable on edge devices. To address this problem, in this paper, we propose a structured knowledge distillation framework, aiming to improve the efficiency of modern vision-only BEV detection models. The proposed framework mainly includes: (a) spatial-temporal distillation which distills teacher knowledge of information fusion from different timestamps and views, (b) BEV response distillation which distills teacher response to different pillars, and (c) weight-inheriting which solves the problem of inconsistent inputs between students and teacher in modern transformer architectures. Experimental results show that our method leads to an average improvement of 2.16 mAP and 2.27 NDS on the nuScenes benchmark, outperforming multiple baselines by a large margin.