Reinforcement learning has shown great promise for synthesizing realistic human behaviors by learning humanoid control policies from motion capture data. However, it is still very challenging to reproduce sophisticated human skills like ballet dance, or to stably imitate long-term human behaviors with complex transitions. The main difficulty lies in the dynamics mismatch between the humanoid model and real humans. That is, motions of real humans may not be physically possible for the humanoid model. To overcome the dynamics mismatch, we propose a novel approach, residual force control (RFC), that augments a humanoid control policy by adding external residual forces into the action space. During training, the RFC-based policy learns to apply residual forces to the humanoid to compensate for the dynamics mismatch and better imitate the reference motion. Experiments on a wide range of dynamic motions demonstrate that our approach outperforms state-of-the-art methods in terms of convergence speed and the quality of learned motions. Notably, we showcase a physics-based virtual character empowered by RFC that can perform highly agile ballet dance moves such as pirouette, arabesque and jet\'e. Furthermore, we propose a dual-policy control framework, where a kinematic policy and an RFC-based policy work in tandem to synthesize multi-modal infinite-horizon human motions without any task guidance or user input. Our approach is the first humanoid control method that successfully learns from a large-scale human motion dataset (Human3.6M) and generates diverse long-term motions. Code and videos are available at https://www.ye-yuan.com/rfc.

Most real-world knowledge graphs are characterized by a long-tail relation frequency distribution where a significant fraction of relations occurs only a handful of times. This observation has given rise to recent interest in low-shot learning methods that are able to generalize from only a few examples. The existing approaches, however, are tailored to static knowledge graphs and not easily generalized to temporal settings, where data scarcity poses even bigger problems, e.g., due to occurrence of new, previously unseen relations. We address this shortcoming by proposing a one-shot learning framework for link prediction in temporal knowledge graphs. Our proposed method employs a self-attention mechanism to effectively encode temporal interactions between entities, and a network to compute a similarity score between a given query and a (one-shot) example. Our experiments show that the proposed algorithm outperforms the state of the art baselines for two well-studied benchmarks while achieving significantly better performance for sparse relations.

This paper shows how to construct knowledge graphs (KGs) from pre-trained language models (e.g., BERT, GPT-2/3), without human supervision. Popular KGs (e.g, Wikidata, NELL) are built in either a supervised or semi-supervised manner, requiring humans to create knowledge. Recent deep language models automatically acquire knowledge from large-scale corpora via pre-training. The stored knowledge has enabled the language models to improve downstream NLP tasks, e.g., answering questions, and writing code and articles. In this paper, we propose an unsupervised method to cast the knowledge contained within language models into KGs. We show that KGs are constructed with a single forward pass of the pre-trained language models (without fine-tuning) over the corpora. We demonstrate the quality of the constructed KGs by comparing to two KGs (Wikidata, TAC KBP) created by humans. Our KGs also provide open factual knowledge that is new in the existing KGs. Our code and KGs will be made publicly available.

My opinions are my own. An introduction to the harm that ML systems cause and to the power imbalance that exists between ML system developers and ML system participants …and 10 concrete ways for machine learning practitioners to help build fairer ML systems. Image description: Photo of Black Lives Matter protesters in Washington, D.C. -- 2 signs say "Black Lives Matter" and "White Silence is Violence." Machine learning systems are increasingly used as tools of oppression. All too often, they're used in high-stakes processes without participants' consent and with no reasonable opportunity for participants to contest the system's decisions -- like when risk assessment systems are used by child welfare services to identify at-risk children; when a machine learning (or "ML") model decides who sees which online ads for employment, housing, or credit opportunities; or when facial recognition systems are used to surveil neighborhoods where Black and Brown people live. In reality though, machine learning systems reflect the beliefs and biases of those who design and develop them.

The golden age of drone delivery has begun. Did you know drones and their associated functions are a $50 billion industry by 2023? Industry experts are predicting unprecedented use in previously unimaginable applications with deep-learning now powering these drones. Drone delivery services has become an essential tool in fighting the COVID-19 pandemic, helping to create contactless delivery and resilient supply chain services. The retail industry is leading the way in adopting drone delivery services among both consumers and companies.

If you think that the Sahara is covered only by golden dunes and scorched rocks, you aren't alone. In an area of West Africa 30 times larger than Denmark, an international team, led by University of Copenhagen and NASA researchers, has counted over 1.8 billion trees and shrubs. The 1.3 million km2 area covers the western-most portion of the Sahara Desert, the Sahel and what are known as sub-humid zones of West Africa. "We were very surprised to see that quite a few trees actually grow in the Sahara Desert, because up until now, most people thought that virtually none existed. We counted hundreds of millions of trees in the desert alone. Doing so wouldn't have been possible without this technology. Indeed, I think it marks the beginning of a new scientific era," asserts Assistant Professor Martin Brandt of the University of Copenhagen's Department of Geosciences and Natural Resource Management, lead author of the study's scientific article, now published in Nature.

In an area of West Africa 30 times larger than Denmark, an international team, led by University of Copenhagen and NASA researchers, has counted over 1.8 billion trees and shrubs. The 1.3 million km2 area covers the western-most portion of the Sahara Desert, the Sahel and what are known as sub-humid zones of West Africa. "We were very surprised to see that quite a few trees actually grow in the Sahara Desert, because up until now, most people thought that virtually none existed. We counted hundreds of millions of trees in the desert alone. Doing so wouldn't have been possible without this technology. Indeed, I think it marks the beginning of a new scientific era," asserts Assistant Professor Martin Brandt of the University of Copenhagen's Department of Geosciences and Natural Resource Management, lead author of the study's scientific article, now published in Nature.

Previously an academic, Vivienne Ming initially regretted her decision to become an entrepreneur. Her first project combined neuroscience and artificial intelligence and education. Thinking she could change the world, she created amazing technologies, that everyone she demonstrated to loved. However, investors didn't see the opportunity and didn't want to work with her. Instead, they wanted to buy the entire product and appoint their own CEO's.

Nigerian Pidgin remains one of the most popular languages in West Africa. With at least 75 million speakers along the West African coast, the language has spread to diasporic communities through Nigerian immigrants in England, Canada, and America, amongst others. In contrast, the language remains an under-resourced one in the field of natural language processing, particularly on speech recognition and translation tasks. In this work, we present the first parallel (speech-to-text) data on Nigerian pidgin. We also trained the first end-to-end speech recognition system (QuartzNet and Jasper model) on this language which were both optimized using Connectionist Temporal Classification (CTC) loss. With baseline results, we were able to achieve a low word error rate (WER) of 0.77% using a greedy decoder on our dataset. Finally, we open-source the data and code along with this publication in order to encourage future research in this direction.

This work proposes a novel tensor train random projection (TTRP) method for dimension reduction, where the pairwise distances can be approximately preserved. Based on the tensor train format, this new random projection method can speed up the computation for high dimensional problems and requires less storage with little loss in accuracy, compared with existing methods (e.g., very sparse random projection). Our TTRP is systematically constructed through a rank-one TT-format with Rademacher random variables, which results in efficient projection with small variances. The isometry property of TTRP is proven in this work, and detailed numerical experiments with data sets (synthetic, MNIST and CIFAR-10) are conducted to demonstrate the efficiency of TTRP.