I created a lyrics generator that seems simple, but actually ended up involving around 50 hours of programming. But the result of that was still poetry, so I added a bunch of non-ML post-processing steps to make it look like song lyrics. After GPT-2 produces the raw content, I use the first 6 lines and call that the "Verse 1", then the next 4 lines are the "Chorus", then the next 6 lines as "Verse 2", and then to make the chorus sound like a chorus, I repeat the first chorus again. I also make all sorts of other small adjustments like filtering out r-rated content, deleting the last line of the raw lyrics because most of the time it is unfinished (cut off), deleting lines that get repeated too much, and getting a whole new set of lyrics if the lyrics become too short after all the deletions. Sometimes the lyrics have phrases like [Repeat Chorus] or (instrumental break) which are no good, so I automatically delete those lines also.

The resulting applications include everything from cryptography and optimization to machine learning and materials science.

By 2022, 40% of machine learning model development and scoring will be done in products that do not have machine learning as their primary goal.

Zegami's statement claims that it will also be vital in the development of artificial intelligence, where machines and computers will increasingly make …

The company employs engineers in Seattle on machine–learning technology.

It is a crucial step to achieve effective semantic segmentation of lane marking during the construction of the lane level high-precision map. In recent years, many image semantic segmentation methods have been proposed. These methods mainly focus on the image from camera, due to the limitation of the sensor itself, the accurate three-dimensional spatial position of the lane marking cannot be obtained, so the demand for the lane level high-precision map construction cannot be met. This paper proposes a lane marking semantic segmentation method based on LIDAR and camera fusion deep neural network. Different from other methods, in order to obtain accurate position information of the segmentation results, the semantic segmentation object of this paper is a bird's eye view converted from a LIDAR points cloud instead of an image captured by a camera. This method first uses the deeplabv3+ [\ref{ref:1}] network to segment the image captured by the camera, and the segmentation result is merged with the point clouds collected by the LIDAR as the input of the proposed network. In this neural network, we also add a long short-term memory (LSTM) structure to assist the network for semantic segmentation of lane markings by using the the time series information. The experiments on more than 14,000 image datasets which we have manually labeled and expanded have shown the proposed method has better performance on the semantic segmentation of the points cloud bird's eye view. Therefore, the automation of high-precision map construction can be significantly improved. Our code is available at https://github.com/rolandying/FusionLane.

Today text classification models have been widely used. However, these classifiers are found to be easily fooled by adversarial examples. Fortunately, standard attacking methods generate adversarial texts in a pair-wise way, that is, an adversarial text can only be created from a real-world text by replacing a few words. In many applications, these texts are limited in numbers, therefore their corresponding adversarial examples are often not diverse enough and sometimes hard to read, thus can be easily detected by humans and cannot create chaos at a large scale. In this paper, we propose an end to end solution to efficiently generate adversarial texts from scratch using generative models, which are not restricted to perturbing the given texts. We call it unrestricted adversarial text generation. Specifically, we train a conditional variational autoencoder (VAE) with an additional adversarial loss to guide the generation of adversarial examples. Moreover, to improve the validity of adversarial texts, we utilize discrimators and the training framework of generative adversarial networks (GANs) to make adversarial texts consistent with real data. Experimental results on sentiment analysis demonstrate the scalability and efficiency of our method. It can attack text classification models with a higher success rate than existing methods, and provide acceptable quality for humans in the meantime.

Game of Thrones, touchscreen devices, and superhero movies: those things have little in common apart from the fact that they went through a meteoric rise in the 2010s. Still, if you believe what AI experts have to say, they pale in comparison to the largest tech phenomenon of the decade: Big Data. The'old' generation of data scientists still remember the days they were telling their manager (usually, someone with no expertise in machine learning) that gathering data would take months. And, honestly, it really did. For example, in the early days of the digital era, continuously sharing data on social media was still uncommon behavior, and it would take months for companies to collect what can be collected in just days (if not hours) today.