A dynamic short-film that merges cinematic storytelling, artificial intelligence, and user interactivity, Agence is never the same twice. In this simulated universe, you have the power to observe or interfere with tiny AI creatures, called the “Agents”, as they react to each other and their emerging world. Once you meet these little AI creatures, their story will never be the same. Read More
Daily Archives: October 21, 2020
Understanding the Role of Individual Units in a Deep Neural Network
Deep neural networks excel at finding hierarchical representations that solve complex tasks over large data sets. How can we humans understand these learned representations? In this work, we present network dissection, an analytic framework to systematically identify the semantics of individual hidden units within image classification and image generation networks. First, we analyze a convolutional neural network (CNN) trained on scene classification and discover units that match a diverse set of object concepts. We find evidence that the network has learned many object classes that play crucial roles in classifying scene classes. Second, we use a similar analytic method to analyze a generative adversarial network (GAN) model trained to generate scenes. By analyzing changes made when small sets of units are activated or deactivated, we find that objects can be added and removed from the output scenes while adapting to the context. Finally, we apply our analytic framework to understanding adversarial attacks and to semantic image editing. Read More
#gans, #neural-networksEye on A.I. Episode 44 – Fei-Fei Li
This week I speak to Stanford professor Fei-Fei Li, one of the people responsible for the current AI revolution. Fei-Fei talked about her early days running a New Jersey dry cleaner to finance her Princeton education, her creation of ImageNet, the world’s first large labeled image data set, which allowed the validation of neural networks, and her latest work on ambient intelligence, which promises to transform elder care. Read More
The Ultimate Python Resource hub
Programming language Python is a big hit for machine learning. But now it needs to change
Despite its popularity, Python could become limited to data science alone on its current trajectory, say two experts.
Open-source programming language Python has become one of the few languages that won’t disappear anytime soon. It’s the top or one of the top two languages in most notable language popularity indexes, and even looks set to beat Java these days.
But 35-year-old Python does have its weaknesses. Not necessarily for the data-science and machine-learning communities built around Python extensions like NumPy and skippy, but as a general programming language. Read More
Is Artificial Intelligence Closer to Common Sense?
Artificial intelligence researchers have not been successful in giving intelligent agents the common-sense knowledge they need to reason about the world. Without this knowledge, it is impossible for intelligent agents to truly interact with the world. Traditionally, there have been two unsuccessful approaches to getting computers to reason about the world—symbolic logic and deep learning. A new project, called COMET, tries to bring these two approaches together. Although it has not yet succeeded, it offers the possibility of progress. Read More
Creating Next-Gen Video Game AI With Reinforcement Learning
Learn how reinforcement learning is being used to upend traditional methods of creating video game AI
Reinforcement learning stands to become the new gold standard in creating intelligent video game AI. The chief advantage of reinforcement learning(RL) over traditional game AI methods is that, rather than hand-crafting the AI’s logic using complicated behavior trees, with RL one simply rewards the behavior they wish the AI to manifest and the agent learns by itself to perform the necessary sequence of actions to achieve the desired behavior. In essence, this is how one might teach a dog to perform tricks using a food reward.
The RL approach to game AI can be used to train a variety of strategic behaviors, including path finding, NPC attack and defense, and almost every behavior a human is capable of exhibiting while playing a video game. Read More
How Google Is Using AI & ML To Improve Search Experience
Recently, the developers at Google detailed the methods and ways they have been using artificial intelligence and machine learning in order to improve its search experience. The announcements were made during the Search On 2020 event, where the tech giant unveiled several enhancements in AI that will help to get search results in the coming years. Read More
#nlp, #big7
Rick's Cafe AI 