#neural networking

[kreuzaderny]

[alpha-beta-gamer]

Drucker tasks you with evolving the neural network-based racing skills of AI controlled bots over many generations then racing them in tournaments against the Drucker AI.

Read More & Play The Beta, Free (Windows)

[onclickonload]

Neural networking gender prediction - Javascript Solutions

Cool way to get started with Artificial Neural Networking aka ANN, Neural networking gender prediction using node js package Synaptic js

[kreuzaderny]

With questionable copyright claim, Jay-Z orders deepfake audio parodies off YouTube

Over the weekend, for the first time, the anonymous creator of Vocal Synthesis received a copyright claim on YouTube, taking two of his videos offline with deepfaked audio of Jay-Z reciting the “To Be or Not To Be” soliloquy from Hamlet and Billy Joel’s “We Didn’t Start the Fire.”

According to the creator, the copyright claims were filed by Roc Nation LLC with an unusual reason for removal: “This content unlawfully uses an AI to impersonate our client’s voice.”

[kreuzaderny]

Defending Against Neural Fake News

Recent progress in natural language generation has raised dual-use concerns. While applications like summarization and translation are positive, the underlying technology also might enable adversaries to generate neural fake news: targeted propaganda that closely mimics the style of real news. Modern computer security relies on careful threat modeling: identifying potential threats and vulnerabilities from an adversary's point of view, and exploring potential mitigations to these threats. Likewise, developing robust defenses against neural fake news requires us first to carefully investigate and characterize the risks of these models. We thus present a model for controllable text generation called Grover. Given a headline like `Link Found Between Vaccines and Autism,' Grover can generate the rest of the article; humans find these generations to be more trustworthy than human-written disinformation. Developing robust verification techniques against generators like Grover is critical. We find that best current discriminators can classify neural fake news from real, human-written, news with 73% accuracy, assuming access to a moderate level of training data. Counterintuitively, the best defense against Grover turns out to be Grover itself, with 92% accuracy, demonstrating the importance of public release of strong generators. We investigate these results further, showing that exposure bias -- and sampling strategies that alleviate its effects -- both leave artifacts that similar discriminators can pick up on. We conclude by discussing ethical issues regarding the technology, and plan to release Grover publicly, helping pave the way for better detection of neural fake news.

[kreuzaderny]

Brain implants that let you speak your mind

The researchers worked with five volunteers who were undergoing a procedure termed intracranial monitoring, in which electrodes are used to monitor brain activity as part of a treatment for epilepsy. The authors used a technique called high-density electrocorticography to track the activity of areas of the brain that control speech and articulator movement as the volunteers spoke several hundred sentences. To reconstruct speech, rather than transforming brain signals directly into audio signals, Anumanchipalli et al. used a two-stage decoding approach in which they first transformed neural signals into representations of movements of the vocal-tract articulators, and then transformed the decoded movements into spoken sentences (Fig. 1). Both of these transformations used recurrent neural networks — a type of artificial neural network that is particularly effective at processing and transforming data that have a complex temporal structure.

[kreuzaderny]

Self-supervised Anomaly Detection for Narrowband SETI

 The Search for Extra-terrestrial Intelligence (SETI) aims to find technological signals of extra-solar origin. Radio frequency SETI is characterized by large unlabeled datasets and complex interference environment. The infinite possibilities of potential signal types require generalizable signal processing techniques with little human supervision. We present a generative model of self-supervised deep learning that can be used for anomaly detection and spatial filtering. We develop and evaluate our approach on spectrograms containing narrowband signals collected by Breakthrough Listen at the Green Bank telescope. The proposed approach is not meant to replace current narrowband searches but to demonstrate the potential to generalize to other signal types.

[kreuzaderny]

DeepMasterPrint: Fingerprint Spoofing via Latent Variable Evolution

Biometric authentication is important for a large range of systems, including but not limited to consumer electronic devices such as phones. Understanding the limits of and attacks on such systems is therefore crucial. This paper presents an attack on fingerprint recognition system using MasterPrints, synthetic fingerprints that are capable of spoofing multiple people's fingerprints. The method described is the first to generate complete image-level Masterprints, and further exceeds the attack accuracy of previous methods that could not produce complete images. The method, Latent Variable Evolution, is based on training a Generative Adversarial Network on a set of real fingerprint images. Stochastic search in the form of the Covariance Matrix Adaptation Evolution Strategy is then used to search for latent variable (inputs) to the generator network that optimize the number of matches from a fingerprint recognizer. We find MasterPrints that a commercial fingerprint system matches to 23% of all users in a strict security setting, and 77% of all users at a looser security setting. The underlying method is likely to have broad usefulness for security research as well as in aesthetic domains.