While researchers say travel does affect the brain’s neural pathways, true empathy remains an elusive destination.

Deep learning has come a long way since the days it could only recognize hand-written characters on checks and envelopes. Today, deep neural networks have become a key component of many computer vision applications, from photo and video editors to medical software and self-driving cars. Roughly fashioned after the structure of the brain, neural networks have come […]

These stories are bound to get your imagination all atwitter ahead of the new year. 2021 was a banner year for breakthroughs.

N/A

Neural network walking simulator. (GAN/ pix2pix)

Welcome to Neural’s beginner’s guide to AI. This long-running series should provide you with a very basic understanding of what AI is, what it can do, and how it works. In addition to the article you’re currently reading, the guide contains articles on (in order published) neural networks, computer vision, natural language processing, algorithms, artificial […]

The human mind has different mechanisms for processing individual pieces of information and sequences. For instance, we have a definition of the word “like.” But we also know that ...

"Dojo" supercomputer will train neural networks that power self-driving software.

The site of Sid.

Intel Macs' lack of an equivalent to the M1's Neural Engine may be to blame.

Neurotech start-up shows how device can broadcast pig’s neural activity

The only difference between science fiction and science is patience. Yesterday's mainframes are today's smartphones and today's neural networks will be tomorrow's androids. But long ...

NVIDIA Research has invented a way to use AI to dramatically reduce video call bandwidth while simultaneously improving quality. What the researchers have

What is the master algorithm that allows humans to be so efficient at learning things? That is a question that has perplexed artificial intelligence scientists and researchers who, ...

This article is part of our reviews of AI research papers, a series of posts that explore the latest findings in artificial intelligence. Consider the animal in the following image. ...

Neurotech start-up shows how device can broadcast pig’s neural activity

Programmable control of hydrogen atoms allows switching between useful states.

A library to train large neural networks across the internet. Imagine training one huge transformer on thousands of computers from universities, companies, and volunteers.

Spiking neural networks combine analog computation with event-based communication using discrete spikes. While the impressive advances of deep learning are enabled by training non-spiking artificial neural networks using the backpropagation algorithm, applying this algorithm to spiking networks was previously hindered by the existence of discrete spike events and discontinuities. For the first time, this work derives the backpropagation algorithm for a continuous-time spiking neural network and a general loss function by applying the adjoint method together with the proper partial derivative jumps, allowing for backpropagation through discrete spike events without approximations. This algorithm, EventProp, backpropagates errors at spike times in order to compute the exact gradient in an event-based, temporally and spatially sparse fashion. We use gradients computed via EventProp to train networks on the Yin-Yang and MNIST datasets using either a spike time or voltage based loss function and report competitive performance. Our work supports the rigorous study of gradient-based learning algorithms in spiking neural networks and provides insights toward their implementation in novel brain-inspired hardware.

N/A

Human brains have neurons related to specific people, called grandmother cells, and now these have also been identified in artificial neural networks

This article is part of our reviews of AI research papers, a series of posts that explore the latest findings in artificial intelligence. With their millions and billions of numerical ...

N/A

Deep neural networks have a huge advantage They replace “feature engineering”—a difficult and arduous part of the classic machine learning cycle—with an end-to-end process ...

One of the most influential technologies of the past decade is artificial neural networks, the fundamental piece of deep learning algorithms, the bleeding edge of artificial intelligence. You ...

Tensors and Dynamic neural networks in Python with strong GPU acceleration - pytorch/pytorch

Guitar plugin made with JUCE that uses neural network models to emulate real world hardware. - keyth72/SmartGuitarAmp

Greetings carbon-based life forms! I'm excited to announce the Neural track at TNW Conference 2021. Neural is known as TNW's artificial intelligence vertical, but I'm here to tell ...

So you’re interested in AI? Then join our online event, TNW2020, where you’ll hear how artificial intelligence is transforming industries and businesses. The Game of Life is a grid-based automaton that is very popular in discussions about science, computation, and artificial intelligence. It is an interesting idea that shows how very simple rules can yield […]

Neural stem cells with the Neanderthal version of a key gene behave differently.

Today, artificial intelligence is mostly about artificial neural networks and deep learning. But this is not how it always was. In fact, for most of its six-decade history, the field ...

In recent years, neural networks have shown impressive performance gains on long-standing AI problems, and in particular, answering queries from natural language text. These advances raise the question of whether they can be extended to a point where we can relax the fundamental assumption of database management, namely, that our data is represented as fields of a pre-defined schema. This paper presents a first step in answering that question. We describe NeuralDB, a database system with no pre-defined schema, in which updates and queries are given in natural language. We develop query processing techniques that build on the primitives offered by the state of the art Natural Language Processing methods. We begin by demonstrating that at the core, recent NLP transformers, powered by pre-trained language models, can answer select-project-join queries if they are given the exact set of relevant facts. However, they cannot scale to non-trivial databases and cannot perform aggregation queries. Based on these findings, we describe a NeuralDB architecture that runs multiple Neural SPJ operators in parallel, each with a set of database sentences that can produce one of the answers to the query. The result of these operators is fed to an aggregation operator if needed. We describe an algorithm that learns how to create the appropriate sets of facts to be fed into each of the Neural SPJ operators. Importantly, this algorithm can be trained by the Neural SPJ operator itself. We experimentally validate the accuracy of NeuralDB and its components, showing that we can answer queries over thousands of sentences with very high accuracy.

Welcome to Neural’s beginner’s guide to AI. This multi-part feature should provide you with a very basic understanding of what AI is, what it can do, and how it works. The guide contains articles on (in order published) neural networks, computer vision, natural language processing, algorithms, artificial general intelligence, and the difference between video game AI and real AI.  […]

The creation and development of a robust neural network is a labor-intensive and time consuming endeavor. That's why a team of IBM researchers recently developed a way for AI developers ...

Deep learning is a group of exciting new technologies for neural networks. Through a combination of advanced training techniques and neural network architectural components, it is now possible to create neural networks that can handle tabular data, images, text, and audio as both input and output. Deep learning allows a neural network to learn hierarchies of information in a way that is like the function of the human brain. This course will introduce the student to classic neural network structures, Convolution Neural Networks (CNN), Long Short-Term Memory (LSTM), Gated Recurrent Neural Networks (GRU), General Adversarial Networks (GAN), and reinforcement learning. Application of these architectures to computer vision, time series, security, natural language processing (NLP), and data generation will be covered. High-Performance Computing (HPC) aspects will demonstrate how deep learning can be leveraged both on graphical processing units (GPUs), as well as grids. Focus is primarily upon the application of deep learning to problems, with some introduction to mathematical foundations. Readers will use the Python programming language to implement deep learning using Google TensorFlow and Keras. It is not necessary to know Python prior to this book; however, familiarity with at least one programming language is assumed.

Nvidia Maxine uses Generative Adversarial Networks to re-create video frames.

Pac-Man’s 40th anniversary is May 22, 2020, and to celebrate it, Nvidia used an artificial intelligence model called GameGAN (based on neural networks) to re-create the 8-bit arcade game. The technology could have applications in game development and other fields.

Technologists and investors have high hopes that advances in artificial intelligence, particularly neural networks, will revolutionize the field of brain computing,

Last time, we briefly mentioned the high-level differences between Stockfish and Leela Chess. To recap, Stockfish evaluates about 100 million positions per second using rudimentary heuristics, wher…

Neural-networks have seen a surge of interest for the interpretation of seismic images during the last few years. Network-based learning methods can provide fast and accurate automatic interpretation, provided there are sufficiently many training labels. We provide an introduction to the field aimed at geophysicists that are familiar with the framework of forward modeling and inversion. We explain the similarities and differences between deep networks to other geophysical inverse problems and show their utility in solving problems such as lithology interpolation between wells, horizon tracking and segmentation of seismic images. The benefits of our approach are demonstrated on field data from the Sea of Ireland and the North Sea.

New research that used machine learning tools to identify climate trends says that a critical global warming threshold could be closer than we think. The study, published this week in the Proceedings of the National Academy of Science, used artificial neural networks trained on climate model output to predict the time…Read more...

When Yann LeCun founded the Facebook AI Research (FAIR) lab in 2013, artificial intelligence was entering a boom period that his research helped trigger.   Facebook’s chief AI scientist had been among a group of computer scientists who retained faith in deep neural networks during an “AI winter” of reduced funding and interest in the field. In […]

In recent years, deep learning has proven to be an effective solution to many of the hard problems of artificial intelligence. But deep learning is also becoming increasingly expensive. Running deep neural networks requires a lot of compute resources, training them even more. The costs of deep learning are causing several challenges for the artificial intelligence […]

With machine learning becoming increasingly popular, one thing that has been worrying experts is the security threats the technology will entail. We are still exploring the possibilities The breakdown of autonomous driving systems? Inconspicuous theft of sensitive data from deep neural networks? Failure of deep learning–based biometric authentication? Subtle bypass of content moderation algorithms? Meanwhile, machine […]

Anchor Neural World (ANW) Achieves Market Cap of $350,744.94

Delivering malware covertly and detection-evadingly is critical to advanced malware campaigns. In this paper, we present a method that delivers malware covertly and detection-evadingly through neural network models. Neural network models are poorly explainable and have a good generalization ability. By embedding malware into the neurons, malware can be delivered covertly with minor or even no impact on the performance of neural networks. Meanwhile, since the structure of the neural network models remains unchanged, they can pass the security scan of antivirus engines. Experiments show that 36.9MB of malware can be embedded into a 178MB-AlexNet model within 1% accuracy loss, and no suspicious are raised by antivirus engines in VirusTotal, which verifies the feasibility of this method. With the widespread application of artificial intelligence, utilizing neural networks becomes a forwarding trend of malware. We hope this work could provide a referenceable scenario for the defense on neural network-assisted attacks.

We study the problem of learning efficient algorithms that strongly generalize in the framework of neural program induction. By carefully designing the input / output interfaces of the neural model and through imitation, we are able to learn models that produce correct results for arbitrary input sizes, achieving strong generalization. Moreover, by using reinforcement learning, we optimize for program efficiency metrics, and discover new algorithms that surpass the teacher used in imitation. With this, our approach can learn to outperform custom-written solutions for a variety of problems, as we tested it on sorting, searching in ordered lists and the NP-complete 0/1 knapsack problem, which sets a notable milestone in the field of Neural Program Induction. As highlights, our learned model can perform sorting perfectly on any input data size we tested on, with $O(n log n)$ complexity, whilst outperforming hand-coded algorithms, including quick sort, in number of operations even for list sizes far beyond those seen during training.

A few weeks ago, The New Yorker magazine published a story titled “Total Recall,” in which one of their correspondents, Patrick Radden Keefe, traveled to England to interview a team of “super-recognizers.” While most humans have spots of trouble putting names to faces, super-recognizers have an uncanny ability to recognize human faces. The city of London is known for a relatively high number of security cameras, and the city’s Metropolitan Police Service has begun employing these super-recognizers to comb through footage of unsolved crimes. The results have been successful, and other police departments around the world are now considering similar tactics. When asked about the possibility of a computer program aiding in the process of facial recognition, the idea was entirely dismissed by several of these super-recognizers. Although technology is not replacing super-recognizers yet, researchers from the Center for Data Science have been working to bridge the gap between human and machine visual recognition for quite some time, and with promising results. In 2014, three researchers from NYU—Avi Ziskind, a former Postdoctoral Researcher at NYU’s Psychology department, Yann LeCunn, from the Center for Data Science, and Denis Pelli, from NYU’s Computer Science Department—gave a presentation titled, “Two Machine-Learning Models of Object Recognition Exhibit Key Feature of Human Performance” at the 2014 Moore-Sloan Data Science Initiative Launch Event. They presented their research on two machine-learning models that had been trained to exhibit human-like levels of object recognition. The first model was a convolutional neural network, a type of model that is loosely based on the ways in which the human brain functions. The second was a texture statistics model, which measures the probability that a given image matches a previously known image. When given pieces of text, the models displayed two hallmarks of human recognition an understanding of both spatial frequency and font complexity. In The New Yorker article, the possibility of computer-based facial recognition was partially dismissed because super-recognizers often deal with grainy footage, or images that are poorly lit. But the models developed by Ziskind, LeCunn, and Pelli were well equipped to deal with visual noise, at least in the case of text. The two graphs below measure the neural network’s performance against a human observer. The network was trained to accommodate for two types of visual noise which are also present in human vision white noise and 1/f noise. When trained for both types of noises, the threshold curve for the neural network was remarkably similar to the threshold curve for human vision, and in some cases, the neural network exhibited a higher threshold for recognizing text. The texture statistics model did not perform as closely to its human vision counterpart, but still performed well overall. While text analysis is a different beast than facial recognition, the core concepts are not fundamentally different. The work of Ziskind, LeCunn, and Pelli shows that computer facial recognition may be much closer closer than we think.

Who needs strategies when you've got the finest neural networks known to machines?