GIIS AI & Emerging Tech Community

GIIS AI & Emerging Tech Community Building community to share resources, conduct discourse & organize educational & research activities around AI & Emerging Tech for Sustainable Future.

Join our online community in Discord: https://discord.gg/AfvSmjyZz6

TEJ Fellowship Application is now OPENPlease fill the application form to apply for TEJ Fellowship. You can find the li...
22/03/2022

TEJ Fellowship Application is now OPEN
Please fill the application form to apply for TEJ Fellowship. You can find the link to apply at https://www.tejcenter.org/.
TEJ Fellowship is a 10-month Full-Time Software Engineering Course. TEJ is currently looking for six individuals from marginalized communities that are committed to becoming software engineers. The selected fellows will be provided with a monthly stipend of Rs. 15,000/- and trained in coding and communications skills required to succeed in professional settings.

At TEJ Fellowship, we recruit and invest in candidates from marginalized and underrepresented communities in technology.

"Fundamental mathematical results had suggested that networks should only need to be so big, but modern neural networks ...
18/02/2022

"Fundamental mathematical results had suggested that networks should only need to be so big, but modern neural networks are commonly scaled up far beyond that predicted requirement — a situation known as overparameterization.

In a paper presented in December at NeurIPS, a leading conference, Sébastien Bubeck of Microsoft Research and Mark Sellke of Stanford University provided a new explanation for the mystery behind scaling’s success. They show that neural networks must be much larger than conventionally expected to avoid certain basic problems. The finding offers general insight into a question that has persisted over several decades...

In their new proof, the pair show that overparameterization is necessary for a network to be robust. They do it by figuring out how many parameters are needed to fit data points with a curve that has a mathematical property equivalent to robustness: smoothness.

To see this, again imagine a curve in the plane, where the x-coordinate represents the color of a single pixel, and the y-coordinate represents an image label. Since the curve is smooth, if you were to slightly modify the pixel’s color, moving a short distance along the curve, the corresponding prediction would only change a small amount. On the other hand, for an extremely jagged curve, a small change in the x-coordinate (the color) can lead to a dramatic change in the y-coordinate (the image label). Giraffes can become gerbils."

Two researchers show that for neural networks to be able to remember better, they need far more parameters than previously thought.

"In collaboration with the Swiss Plasma Center at EPFL—a university in Lausanne, Switzerland—the UK-based AI firm has no...
18/02/2022

"In collaboration with the Swiss Plasma Center at EPFL—a university in Lausanne, Switzerland—the UK-based AI firm has now trained a deep reinforcement learning algorithm to control the superheated soup of matter inside a nuclear fusion reactor. The breakthrough, published in the journal Nature, could help physicists better understand how fusion works, and potentially speed up the arrival of an unlimited source of clean energy...

Controlling nuclear fusion on Earth is hard, however. The problem is that atomic nuclei repel each other. Smashing them together inside a reactor can only be done at extremely high temperatures, often reaching hundreds of millions of degrees—hotter than the center of the sun. At these temperatures, matter is neither solid, liquid, nor gas. It enters a fourth state, known as plasma: a roiling, superheated soup of particles...

Controlling the plasma requires constant monitoring and manipulation of the magnetic field. The team trained its reinforcement-learning algorithm to do this inside a simulation. Once it had learned how to control—and change—the shape of the plasma inside a virtual reactor, the researchers gave it control of the magnets in the Variable Configuration Tokamak (TCV), an experimental reactor in Lausanne. They found that the AI was able to control the real reactor without any additional fine-tuning. In total, the AI controlled the plasma for only two seconds—but this is as long as the TCV reactor can run before getting too hot...

The researchers believe that using AI to control plasma will make it easier to experiment with different conditions inside reactors, helping them understand the process and potentially speeding up the development of commercial nuclear fusion. The AI also learned how to control the plasma by adjusting magnets in a way that humans had not tried before, which suggests that there may be new reactor configurations to explore."

The prospect of unlimited clean energy is still a long way off, but this is another example of DeepMind tackling hard real-world problems.

'Previous approaches for visual explanations of classifiers, such as attention maps (e.g., Grad-CAM), highlight which re...
25/01/2022

'Previous approaches for visual explanations of classifiers, such as attention maps (e.g., Grad-CAM), highlight which regions in an image affect the classification, but they do not explain what attributes within those regions determine the classification outcome: For example, is it their color? Their shape? Another family of methods provides an explanation by smoothly transforming the image between one class and another (e.g., GANalyze). However, these methods tend to change all attributes at once, thus making it difficult to isolate the individual affecting attributes.

In “Explaining in Style: Training a GAN to explain a classifier in StyleSpace”, presented at ICCV 2021, we propose a new approach for a visual explanation of classifiers. Our approach, StylEx, automatically discovers and visualizes disentangled attributes that affect a classifier. It allows exploring the effect of individual attributes by manipulating those attributes separately (changing one attribute does not affect others). StylEx is applicable to a wide range of domains, including animals, leaves, faces, and retinal images. Our results show that StylEx finds attributes that align well with semantic ones, generate meaningful image-specific explanations, and are interpretable by people as measured in user studies.

For instance, to understand a cat vs. dog classifier on a given image, StylEx can automatically detect disentangled attributes and visualize how manipulating each attribute can affect the classifier probability. The user can then view these attributes and make semantic interpretations for what they represent. For example, in the figure above, one can draw conclusions such as “dogs are more likely to have their mouth open than cats” (attribute #4 in the GIF above), “cats’ pupils are more slit-like” (attribute #5), “cats’ ears do not tend to be folded” (attribute #1), and so on.'

Posted by Oran Lang and Inbar Mosseri, Software Engineers, Google Research Neural networks can perform certain tasks remarkably well, but...

'Gebru sees her research institute DAIR as another organ within this wider push toward tech that is socially responsible...
23/01/2022

'Gebru sees her research institute DAIR as another organ within this wider push toward tech that is socially responsible, putting the needs of communities ahead of the profit incentive and everything that comes with it. At DAIR, Gebru will work with researchers around the world across multiple disciplines to examine the outcomes of AI technology, with a particular focus on the African continent and the African diaspora in the U.S. One of DAIR’s first projects will use AI to analyze satellite imagery of townships in South Africa, to better understand legacies of apartheid. DAIR is also working on building an industry-wide standard that could help mitigate bias in data sets, by making it common practice for researchers to write accompanying documentation about how they gathered their data, what its limitations are and how it should (or should not) be used. Gebru says DAIR’s funding model gives it freedom too. DAIR has received $3.7 million from a group of big philanthropists including the Ford, MacArthur and Open Society foundations. It’s a novel way of funding AI research, with few ties to the system of Silicon Valley money and patronage that often decides which areas of research are worthy of pursuit, not only within Big Tech companies, but also within the academic institutions to which they give grants.'

'We need to let people who are harmed by technology imagine the future that they want,' Gebru tells TIME

"The researchers have developed a single algorithm that can be used to train a neural network to recognize images, text,...
23/01/2022

"The researchers have developed a single algorithm that can be used to train a neural network to recognize images, text, or speech. The algorithm, called Data2vec, not only unifies the learning process but performs at least as well as existing techniques in all three skills...

Data2vec uses two neural networks, a student and a teacher. First, the teacher network is trained on images, text, or speech in the usual way, learning an internal representation of this data that allows it to predict what it is seeing when shown new examples. When it is shown a photo of a dog, it recognizes it as a dog.

The twist is that the student network is then trained to predict the internal representations of the teacher. In other words, it is trained not to guess that it is looking at a photo of a dog when shown a dog, but to guess what the teacher sees when shown that image.

Because the student does not try to guess the actual image or sentence but, rather, the teacher’s representation of that image or sentence, the algorithm does not need to be tailored to a particular type of input."

The single technique for teaching neural networks multiple skills is a step towards general-purpose AI.

"Humans are biased too and, unlike AIs, “in ways that are very hard to interrogate or correct”. Ultimately, if a theory ...
11/01/2022

"Humans are biased too and, unlike AIs, “in ways that are very hard to interrogate or correct”. Ultimately, if a theory produces less reliable predictions than an AI, it will be hard to argue that the machine is the more biased of the two.

A tougher obstacle to the new science may be our human need to explain the world – to talk in terms of cause and effect...

In 2022, therefore, there is almost no stage of the scientific process where AI hasn’t left its footprint. And the more we draw it into our quest for knowledge, the more it changes that quest. We’ll have to learn to live with that, but we can reassure ourselves about one thing: we’re still asking the questions. As Pablo Picasso put it in the 1960s, “computers are useless. They can only give you answers.”"

Does the advent of machine learning mean the classic methodology of hypothesise, predict and test has had its day?

Address

Chakupat
Lalitpur

Website

Alerts

Be the first to know and let us send you an email when GIIS AI & Emerging Tech Community posts news and promotions. Your email address will not be used for any other purpose, and you can unsubscribe at any time.

Contact The Organization

Send a message to GIIS AI & Emerging Tech Community:

Shortcuts

Share

Category