Daily Archives: September 2, 2020
Toward a machine learning model that can reason about everyday actions
Researchers train a model to reach human-level performance at recognizing abstract concepts in video.
The ability to reason abstractly about events as they unfold is a defining feature of human intelligence. We know instinctively that crying and writing are means of communicating, and that a panda falling from a tree and a plane landing are variations on descending.
…In a new study at the European Conference on Computer Vision this month, researchers unveiled a hybrid language-vision model that can compare and contrast a set of dynamic events captured on video to tease out the high-level concepts connecting them. Read More
Google’s BigBird Model Improves Natural Language and Genomics Processing
Researchers at Google have developed a new deep-learning model called BigBird that allows Transformer neural networks to process sequences up to 8x longer than previously possible. Networks based on this model achieved new state-of-the-art performance levels on natural-language processing (NLP) and genomics tasks.
The team described the model and a set of experiments in a paper published on arXiv. BigBird is a new self-attention model that reduces the neural-network complexity of Transformers, allowing for training and inference using longer input sequences. By increasing sequence length up to 8x, the team was able to achieve new state-of-the-art performance on several NLP tasks, including question-answering and document summarization. The team also used BigBird to develop a new application for Transformer models in genomic sequence representations, improving accuracy over previous models by 5 percentage points. Read More
There Is Hope After All: Quantifying Opinion and Trustworthiness in Neural Networks
Artificial Intelligence (AI) plays a fundamental role in the modern world, especially when used as an autonomous decision maker. One common concern nowadays is “how trustworthy the AIs are.” Human operators follow a strict educational curriculum and performance assessment that could be exploited to quantify how much we entrust them. To quantify the trust of AI decision makers, we must go beyond task accuracy especially when facing limited, incomplete, misleading, controversial or noisy datasets. Toward addressing these challenges, we describe DeepTrust, a Subjective Logic (SL) inspired framework that constructs a probabilistic logic description of an AI algorithm and takes into account the trustworthiness of both dataset and inner algorithmic workings. DeepTrust identifies proper multi-layered neural network (NN) topologies that have high projected trust probabilities, even when trained with untrusted data. We show that uncertain opinion of data is not always malicious while evaluating NN’s opinion and trustworthiness, whereas the disbelief opinion hurts trust the most. Also trust probability does not necessarily correlate with accuracy. DeepTrust also provides a projected trust probability of NN’s prediction, which is useful when the NN generates an over-confident output under problematic datasets. These findings open new analytical avenues for designing and improving the NN topology by optimizing opinion and trustworthiness, along with accuracy, in a multi-objective optimization formulation, subject to space and time constraints. Read More
Trends in Online Influence Efforts
Information and Communications Technologies (ICTs) create novel opportunities for a wide range of political actors. Foreign governments have used social media to influence politics in a range of countries by promoting propaganda, advocating controversial viewpoints, and spreading disinformation. This report updates previous work with data on 76 such foreign influence efforts (FIE) targeting 30 different countries from 2013 through 2019, as well as 20 domestic influence efforts (DIE)in which governments targeted their own citizens. Influence efforts (IEs) are defined as: (i) coordinated campaigns by a state or the ruling party in an autocracy to impact one or more specific aspects of politics at home or in another state, (ii)through media channels, including social media, by (iii) producing content designed to appear indigenous to the target state. The objective of such campaigns can be quite broad and to date have included shaping election outcomes at various levels,shifting the political agenda on topics ranging from health to security, and encouraging political polarization. Our data draw on more than 920 media reports and380 research articles/reports to identify IEs, track their progress, and classify their features. Read More
Rick's Cafe AI 