While deep neural networks (DNNs) are being increasingly used to make predictions from high-dimensional, complex data, they are widely seen as uninterpretable "black boxes", since it can be difficult to discover what input information is used to make predictions. This ability is particularly important for applications in cognitive neuroscience and neuroinformatics. A saliency map is a common approach for producing interpretable visualizations of the relative importance of input features for a prediction. However, many methods for creating these maps fail due to focusing too much on the input or being extremely sensitive to small input noise. It is also challenging to quantitatively evaluate how well saliency maps correspond to the truly relevant input information. In this paper, we develop two quantitative evaluation procedures for saliency methods, using the fact that the Human Connectome Project (HCP) dataset contains functional magnetic resonance imaging (fMRI) data from multiple tasks per subject to create ground truth saliency maps. We then introduce an adversarial training method that makes DNNs robust to small input noise, and demonstrate that it measurably improves interpretability.

Debate about fairness in machine learning has largely centered around competing definitions of what fairness or nondiscrimination between groups requires. However, little attention has been paid to what precisely a group is. Many recent approaches to "fairness" require one to specify a causal model of the data generating process. These exercises make an implicit ontological assumption that a racial or sex group is simply a collection of individuals who share a given trait. We show this by exploring the formal assumption of modularity in causal models, which holds that the dependencies captured by one causal pathway are invariant to interventions on any other pathways. Causal models of sex propose two substantive claims: 1) There exists a feature, sex-on-its-own, that is an inherent trait of an individual that causally brings about social phenomena external to it in the world; and 2) the relations between sex and its effects can be modified in whichever ways and the former feature would still retain the meaning that sex has in our world. We argue that this ontological picture is false. Many of the "effects" that sex purportedly "causes" are in fact constitutive features of sex as a social status. They give the social meaning of sex features, meanings that are precisely what make sex discrimination a distinctively morally problematic type of action. Correcting this conceptual error has a number of implications for how models can be used to detect discrimination. Formal diagrams of constitutive relations present an entirely different path toward reasoning about discrimination. Whereas causal diagrams guide the construction of sophisticated modular counterfactuals, constitutive diagrams identify a different kind of counterfactual as central to an inquiry on discrimination: one that asks how the social meaning of a group would be changed if its non-modular features were altered.

In this paper, we propose enhancing actor-critic reinforcement learning agents by parameterising the final actor layer which produces the actions in order to accommodate the behaviour discrepancy of different actuators, under different load conditions during interaction with the environment. We propose branching the action producing layer in the actor to learn the tuning parameter controlling the activation layer (e.g. Tanh and Sigmoid). The learned parameters are then used to create tailored activation functions for each actuator. We ran experiments on three OpenAI Gym environments, i.e. Pendulum-v0, LunarLanderContinuous-v2 and BipedalWalker-v2. Results have shown an average of 23.15% and 33.80% increase in total episode reward of the LunarLanderContinuous-v2 and BipedalWalker-v2 environments, respectively. There was no significant improvement in Pendulum-v0 environment but the proposed method produces a more stable actuation signal compared to the state-of-the-art method. The proposed method allows the reinforcement learning actor to produce more robust actions that accommodate the discrepancy in the actuators' response functions. This is particularly useful for real life scenarios where actuators exhibit different response functions depending on the load and the interaction with the environment. This also simplifies the transfer learning problem by fine tuning the parameterised activation layers instead of retraining the entire policy every time an actuator is replaced. Finally, the proposed method would allow better accommodation to biological actuators (e.g. muscles) in biomechanical systems.

We modeled the Quora question pairs dataset to identify a similar question. The dataset that we use is provided by Quora. The task is a binary classification. We tried several methods and algorithms and different approach from previous works. For feature extraction, we used Bag of Words including Count Vectorizer, and Term Frequency-Inverse Document Frequency with unigram for XGBoost and CatBoost. Furthermore, we also experimented with WordPiece tokenizer which improves the model performance significantly. We achieved up to 97 percent accuracy. Code and Dataset.

Nils J. Nilsson, a computer scientist who helped develop the first general-purpose robot and was a co-inventor of algorithms that made it possible for the machine to move about efficiently and perform simple tasks, died on Sunday at his home in Medford, Ore. His death was confirmed by his wife, Grace Abbott. Dr. Nilsson was a member of a small group of computer scientists and electrical engineers at the Stanford Research Institute (now known as SRI International) who pioneered technologies that have proliferated in modern life, whether in navigation software used in more than a billion smartphones or in such speech-control systems as Siri. The researchers had been recruited by Charles Rosen, a physicist at the institute, who had raised Pentagon funding in 1966 to design a robot that would be used as a platform for doing research in artificial intelligence. Although the project was intended to create a general-purpose mobile "automaton" and be a test bed for A.I. programs, Mr. Rosen had secured the funding by selling the idea to the Pentagon that the machine would be a mobile sentry for a military base.

As a teenager in Maryland in the 1950s, Mary Allen Wilkes had no plans to become a software pioneer -- she dreamed of being a litigator. One day in junior high in 1950, though, her geography teacher surprised her with a comment: "Mary Allen, when you grow up, you should be a computer programmer!" Wilkes had no idea what a programmer was; she wasn't even sure what a computer was. The first digital computers had been built barely a decade earlier at universities and in government labs. By the time she was graduating from Wellesley College in 1959, she knew her legal ambitions were out of reach. Her mentors all told her the same thing: Don't even bother applying to law school. "They said: 'Don't do it.

In archaeology, there are few watershed moments, when a technological breakthrough changes everything. But the invention of radiocarbon dating in the 1940s brought one such revolution, by providing a consistent, worldwide system for placing archaeological material in chronological order. A more-recent transformative innovation is the airborne application of a remote-sensing technique called light detection and ranging (lidar) to create a model (also known as a digital-elevation model) of the bare-surface terrain that is hidden by trees in forested areas1. Lidar is changing archaeological study of the ancient Maya in Mexico and Central America. It is increasing the speed and scale of discovery, and reshaping our understanding of the antiquity of monumental-scale landscape alteration.

Recently, I was reading Rolf Dobell''s The Art of Thinking Clearly, which made me think about cognitive biases in a way I never had before. I realized how deeply seated some cognitive biases are. In fact, we often don't even consciously realize when our thinking is being affected by one. For data scientists, these biases can really change the way we work with data and make our day-to-day decisions, and generally not for the better. Data science is, despite the seeming objectivity of all the facts we work with, surprisingly subjective in its processes.

Recently, I was reading Rolf Dobell''s The Art of Thinking Clearly, which made me think about cognitive biases in a way I never had before. I realized how deeply seated some cognitive biases are. In fact, we often don't even consciously realize when our thinking is being affected by one. For data scientists, these biases can really change the way we work with data and make our day-to-day decisions, and generally not for the better. Data science is, despite the seeming objectivity of all the facts we work with, surprisingly subjective in its processes.

This Friday, Artificial Intelligence fashion startup Bigthinx, in partnership with Fashinnovation, will live stream the first fully digital 3D Virtual Fashion Show (including digitised human models) since the coronavirus pandemic forced the fashion industry online. The'virtual' aspect is that the models and clothes are being created using 3D digital design, rendering, and animation, based on technical data (including garment measurements) and photographs of the models and clothes. This will be the first time many fashion professionals have seen virtual fashion since the industry-wide discussions about implementing it ramped up, following the coronavirus-induced lockdown. The realization that digital fashion will be a critical long-term solution rather than a temporary measure is evident in industry announcements from Helsinki Fashion Week, the first to declare they will show 3D virtual fashion shows for the upcoming season and beyond, before Covid-19 forced Milan, New York and others to follow suit. In creating this 3D virtual show, with opportunity comes numerous challenges, especially for a technology company known for its'body scan' avatar solution based on just two photos and a selfie from a smartphone.