SRI Blog

-By Han Han, Vincent Lostanlen  New York University Paper Link ABSTRACT  Disentangling and recovering physical attributes, such as shape and material, from a few waveform examples is a challenging inverse problem in audio signal processing, with numerous applications in musical acoustics as well as structural engineering. We propose to address this problem via a combination of time–frequency analysis and supervised machine learning. We start by synthesizing a dataset of sounds using the functional transformation method. Then, we represent each percussive sound in terms of its time-invariant scattering transform coefficients and formulate the parametric estimation of the resonator as multidimensional regression with a deep convolutional neural network. We interpolate scattering coefficients over the surface of the drum as a surrogate for potentially missing data, and study the response of the neural network to interpolated samples. Lastly, we resynthesize drum sounds ...

-By Jonathan Frankle† MIT CSAIL  David J. Schwab CUNY ITS and Ari S. Morcos  of Facebook AI Research Paper link Many important aspects of neural network learning take place within the very earliest iterations or epochs of training.  For example,  Sparse  Trainable sub-networks emerge  Gradient descent moves into a small subspace  Network undergoes a critical period  Researchers examine the changes that deep neural networks undergo during this early phase of training. Over the past decade, methods for successfully training big, deep neural networks have revolutionized machine learning. Yet surprisingly, the underlying reasons for the success of these approaches remain poorly understood, despite remarkable empirical performance. A large body of work has focused on understanding what happens during the later stages of training, while the initial phase has been less explored.  Research is built ...

- By  Andy Coenen, Emily Reif, Ann Yuan Been Kim,  Adam Pearce, Fernanda Viégas, Martin Wattenberg  Google Research Cambridge, MA Paper Link Abstract Transformer architectures show significant promise for natural language processing. Given that a single pretrained model can be fine-tuned to perform well on many different tasks, these networks appear to extract generally useful linguistic features. A natural question is how such networks represent this information internally. This paper describes qualitative and quantitative investigations of one particularly effective model, BERT. At a high level, linguistic features seem to be represented in separate semantic and syntactic subspaces. We find evidence of a fine-grained geometric representation of word senses. We also present empirical descriptions of syntactic representations in both attention matrices and individual word embeddings, as well as a mathematical argument to explain the geometry of thes...

-By Makarand Tapaswi , Yukun Zhu , Rainer Stiefelhagen  Antonio Torralba , Raquel Urtasun , Sanja Fidler  arlsruhe Institute of Technology,  Massachusetts Institute of Technology,  University of Toronto Paper Link Abstract We introduce the MovieQA dataset which aims to evaluate automatic story comprehension from both video and text. The dataset consists of 14,944 questions about 408 movies with high semantic diversity. The questions range from the simpler “Who” did “What” to “Whom”, to “Why” and “How” certain events occurred. Each question comes with a set of five possible answers; a correct one and four deceiving answers provided by human annotators. Our dataset is unique in that it contains multiple sources of information – video clips, plots, subtitles, scripts, and DVS. We analyze our data through various statistics and methods. We further extend existing QA techniques to show that question-answering with such open-ended semantics is...

-By Sara Sabour, Nicholas Frosst,  Geoffrey E. Hinton  Google Brain Toronto Paper Link Abstract   A capsule is a group of neurons whose activity vector represents the instantiation parameters of a specific type of entity such as an object or an object part. We use the length of the activity vector to represent the probability that the entity exists and its orientation to represent the instantiation parameters. Active capsules at one level make predictions, via transformation matrices, for the instantiation parameters of higher-level capsules. When multiple predictions agree, a higher level capsule becomes active. We show that a discrimininatively trained, multi-layer capsule system achieves state-of-the-art performance on MNIST and is considerably better than a convolutional net at recognizing highly overlapping digits. To achieve these results we use an iterative routing-by-agreement mechanism: A lower-level capsule prefers to send its output to higher...

-By Julius Adebayo, Justin Gilmer, Michael Muelly, Ian Goodfellow, Moritz Hardt, Been Kim Google Brain  University of California Berkeley Paper Link This blog post is the fourth part of the Explainable Artificial Intelligence (XAI) series. Refer previous posts link . The post discusses on Salience Mapping techniques, performance, and metrics. Salience Mapping source: Analytics India Magazine The salience map approach is exemplified by occlusion procedure by Zeiler, where a network is repeatedly tested with portions of the input occluded to create a map showing which parts of the data actually have an influence on the network output. Abstract Saliency methods have emerged as a popular tool to highlight features in an input deemed relevant for the prediction of a learned model. Several saliency methods have been proposed, often guided by visual appeal on image data. This paper proposes an actionable methodology to evaluate what kinds of explanations a ...

-By Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin University of Washington  Seattle,  WA 98105, USA Paper Link This is third post in the series of Explainable AI (XAI). Earlier post i shed light on Machine learning impact on models with respect to Biasing. Today's topic is one of the large number of elementary operations , "Linear Proxy Models" (LIME). TRUST I would like to quote Stephen M.R. Covey "THE SPEED OF TRUST" Statements here, which is relevant to Trust. Executive summary link   Simply put, trust means confidence. The opposite of trust — distrust — is suspicion.  Trust always affects two outcomes: speed and cost. When trust goes down, speed goes down and cost goes up. When trust goes up, speed goes up and cost goes down (Strategy x Execution) x Trust = Results Not trusting people is a greater risk. if the users do not trust a model or a prediction, they will not use it.   ...

-By Leilani H. Gilpin, David Bau, Ben Z. Yuan, Ayesha Bajwa, Michael Specter and Lalana Kagal Massachusetts Institute of Technology Cambridge, MA 02139  Paper link Explaining Explanations: An Overview of Interpretability of Machine Learning Explainable AI (XAI), Interpretable AI, or Transparent AI refer to techniques in artificial intelligence (AI) which can be trusted and easily understood by humans. It contrasts with the concept of the "black box" in machine learning where even their designers cannot explain why the AI arrived at a specific decision. XAI can be used to implement a social right to explanation. Some claim that transparency rarely comes for free and that there are often tradeoffs between how "smart" an AI is and how transparent it is; these tradeoffs are expected to grow larger as AI systems increase in internal complexity. The technical challenge of explaining AI decisions is sometimes known as the interpretability problem. So...