Explaining the output of a complicated machine learning model like a deep neural network (DNN) is a central challenge in machine learning. Several proposed local explanation methods address this issue by identifying what dimensions of a single input are most responsible for a DNN's output. The goal of this work is to assess the sensitivity of local explanations to DNN parameter values. Somewhat surprisingly, we find that DNNs with randomly-initialized weights produce explanations that are both visually and quantitatively similar to those produced by DNNs with learned weights. Our conjecture is that this phenomenon occurs because these explanations are dominated by the lower level features of a DNN, and that a DNN's architecture provides a strong prior which significantly affects the representations learned at these lower layers. NOTE: This work is now subsumed by our recent manuscript, Sanity Checks for Saliency Maps (to appear NIPS 2018), where we expand on findings and address concerns raised in Sundararajan et. al. (2018).

Robots require knowledge about objects in order to efficiently perform various household tasks involving objects. The existing knowledge bases for robots acquire symbolic knowledge about objects from manually-coded external common sense knowledge bases such as ConceptNet, Word-Net etc. The problem with such approaches is the discrepancy between human-centric symbolic knowledge and robot-centric object perception due to its limited perception capabilities. Ultimately, significant portion of knowledge in the knowledge base remains ungrounded into robot's perception. To overcome this discrepancy, we propose an approach to enable robots to generate robot-centric symbolic knowledge about objects from their own sensory data, thus, allowing them to assemble their own conceptual understanding of objects. With this goal in mind, the presented paper elaborates on the work-in-progress of the proposed approach followed by the preliminary results.

We present a novel parallelisation scheme that simplifies the adaptation of learning algorithms to growing amounts of data as well as growing needs for accurate and confident predictions in critical applications. In contrast to other parallelisation techniques, it can be applied to a broad class of learning algorithms without further mathematical derivations and without writing dedicated code, while at the same time maintaining theoretical performance guarantees. Moreover, our parallelisation scheme is able to reduce the runtime of many learning algorithms to polylogarithmic time on quasi-polynomially many processing units. This is a significant step towards a general answer to an open question on the efficient parallelisation of machine learning algorithms in the sense of Nick's Class (NC). The cost of this parallelisation is in the form of a larger sample complexity. Our empirical study confirms the potential of our parallelisation scheme with fixed numbers of processors and instances in realistic application scenarios.

In Hindsight Experience Replay (HER), a reinforcement learning agent is trained by treating whatever it has achieved as virtual goals. However, in previous work, the experience was replayed at random, without considering which episode might be the most valuable for learning. In this paper, we develop an energy-based framework for prioritizing hindsight experience in robotic manipulation tasks. Our approach is inspired by the work-energy principle in physics. We define a trajectory energy function as the sum of the transition energy of the target object over the trajectory. We hypothesize that replaying episodes that have high trajectory energy is more effective for reinforcement learning in robotics. To verify our hypothesis, we designed a framework for hindsight experience prioritization based on the trajectory energy of goal states. The trajectory energy function takes the potential, kinetic, and rotational energy into consideration. We evaluate our Energy-Based Prioritization (EBP) approach on four challenging robotic manipulation tasks in simulation. Our empirical results show that our proposed method surpasses state-of-the-art approaches in terms of both performance and sample-efficiency on all four tasks, without increasing computational time. A video showing experimental results is available at https://youtu.be/jtsF2tTeUGQ

We present Spider, a large-scale, complex and cross-domain semantic parsing and text-to-SQL dataset annotated by 11 college students. It consists of 10,181 questions and 5,693 unique complex SQL queries on 200 databases with multiple tables, covering 138 different domains. We define a new complex and cross-domain semantic parsing and text-to-SQL task where different complex SQL queries and databases appear in train and test sets. In this way, the task requires the model to generalize well to both new SQL queries and new database schemas. Spider is distinct from most of the previous semantic parsing tasks because they all use a single database and the exact same programs in the train set and the test set. We experiment with various state-of-the-art models and the best model achieves only 14.3% exact matching accuracy on a database split setting. This shows that Spider presents a strong challenge for future research. Our dataset and task are publicly available at https://yale-lily.github.io/spider

How will our societies evolve with new technologies? This is the question asked by photographer Nicolas Bigot with this series « The Robot Next Door ». This resident of the côtes d'Armor, France, is passionate about science-fiction films and has been a UI/UX designer for ten years. From his studies years in interface design between man and machine for mobile and computer, Nicolas retains an appeal for fantastical subjects. This series is a combination of all his passions.

The researchers from the Medical Research Council (MRC) Cognition and Brain Sciences Unit at the University of Cambridge say this reinforces the need for children to receive detailed assessments of their cognitive skills to identify the best type of support. The study, published in Developmental Science, recruited 550 children who were referred to a clinic -- the Centre for Attention Learning and Memory -- because they were struggling at school. The scientists say that much of the previous research into learning difficulties has focussed on children who had already been given a particular diagnosis, such as attention deficit hyperactivity disorder (ADHD), an autism spectrum disorder, or dyslexia. By including children with all difficulties regardless of diagnosis, this study better captured the range of difficulties within, and overlap between, the diagnostic categories. Dr Duncan Astle from the MRC Cognition and Brain Sciences Unit at the University of Cambridge, who led the study ...

This past April a new video of Barack Obama surfaced on the Internet. Against a backdrop that included both the American and presidential flags, it looked like many of his previous speeches. Wearing a crisp white shirt and dark suit, Obama faced the camera and punctuated his words with outstretched hands: "President Trump is a total and complete dipshit." Without cracking a smile, he continued. "Now, you see, I would never say these things. The view shifted to a split screen, revealing the actor Jordan Peele. Obama hadn't said anything--it was a real recording of an Obama address blended with Peele's impersonation. Side by side, the message continued as Peele, like a digital ventriloquist, put more words in the former president's mouth. In this era of fake news, the video was a public service announcement produced by BuzzFeed News, showcasing an application of new artificial-intelligence (AI) technology that could do for audio and video what Photoshop has done for digital images: ...

Countries, like companies, are fighting to be the best in AI.

Using machine learning - a type of artificial intelligence (AI) - could help develop better predictions of why children struggle at school, scientists say. The researchers from the University of Cambridge in the UK used AI and data from hundreds of children who struggle at school to identify clusters of learning difficulties which did not match the previous diagnosis the children had been given. The finding, published in the journal Developmental Science, reinforces the need for children to receive detailed assessments of their cognitive skills to identify the best type of support. The researchers recruited 550 children who were referred to a clinic because they were struggling at school. Much of the previous research into learning difficulties has focussed on children who had already been given a particular diagnosis, such as attention deficit hyperactivity disorder (ADHD), an autism spectrum disorder, or dyslexia, they said.