Post has shared content
Huge free access medical dataset... The USA National Institutes of Health released over 100,000 anonymized chest x-ray images from over 30,000 patients and data associated to the scientific community (more than 45 GB). For me, datasets availability is the greatest barrier to democratize deep learning.
Add a comment...

Post has shared content
DeepMind WaveNet, which was a research prototype a year ago, is now being used by the Google Assistant to synthesize voices in English and Japanese.

"The new, improved WaveNet model still generates a raw waveform but at speeds 1,000 times faster than the original model, meaning it requires just 50 milliseconds to create one second of speech. In fact, the model is not just quicker, but also higher-fidelity, capable of creating waveforms with 24,000 samples a second. We have also increased the resolution of each sample from 8 bits to 16 bits, the same resolution used in compact discs."

"This makes the new model more natural sounding according to tests with human listeners. For example, the new US English voice I gets a mean-opinion-score (MOS) of 4.347 on a scale of 1-5, where even human speech is rated at just 4.667."
Add a comment...

Post has shared content
Move towards 'holy grail' of computing by creation of brain-like photonic microchips

Scientists have made a crucial step towards unlocking the "holy grail" of computing - microchips that mimic the way the human brain works to store and process information. A research team, including Professor C. David Wright from the University of Exeter, have made a pioneering breakthrough by developing photonic computer chips - that use light rather than electricity - that imitate the way the brain's synapses operate. The work, conducted by researchers from Oxford, Münster and Exeter Universities, combined phase-change materials - commonly found in household items such as re-writable optical discs - with specially designed integrated photonic circuits to deliver a biological-like synaptic response. Crucially, their photonic synapses can operate at speeds a thousand times faster than those of the human brain. The team believe that the research could pave the way for a new age of computing, where machines work and think in a similar way to the human brain, while at the same time exploiting the speed and power efficiency of photonic systems. Professor Harish Bhaskaran from Oxford University and who led the team said "The development of computers that work more like the human brain has been a holy grail of scientists for decades. Via a network of neurons and synapses the brain can process and store vast amounts of information simultaneously, using only a few tens of Watts of power. Conventional computers can't come close to this sort of performance."
Add a comment...

Post has attachment
SNAPPERS FACIAL RIG V2.0

Via https://goo.gl/xUcDgu
Add a comment...

Post has shared content
A neural network for synthesizing high resolution photorealistic images from an "incomplete signal" such as a low-resolution image, a surface normal map (which shows the 2D 'bump' and 'dent' shadows from a 3D surface in light), or image showing edges (like a sketch).

"The first stage uses a convolutional neural network (CNN) to maps the input to a (overly-smoothed) image, and the second stage uses a pixel-wise nearest neighbor method to map the smoothed output to multiple high-quality, high-frequency outputs in a controllable manner. We demonstrate our approach for various input modalities, and for various domains ranging from human faces to cats-and-dogs to shoes and handbags."
Add a comment...

Post has attachment
[...]Remarkably, the neocortex is both complex and simple at the same time. It is complex because it is divided into dozens of regions, each responsible for different cognitive functions. Within each region there are multiple layers of neurons, as well as dozens of neuron types, and the neurons are connected in intricate patterns.
The neocortex is also simple because the details in every region are nearly identical. Through evolution, a single algorithm developed that can be applied to all the things a neocortex does. The existence of such a universal algorithm is exciting because if we can figure out what that algorithm is, we can get at the heart of what it means to be intelligent, and incorporate that knowledge into future machines.[...]
Add a comment...

Post has shared content
A new neural network architecture called the Transformer outperforms both recurrent and convolutional models on academic English to German and English to French translation benchmarks. "On top of higher translation quality, the Transformer requires less computation to train and is a much better fit for modern machine learning hardware, speeding up training by up to an order of magnitude."

"Deciding on the most likely meaning and appropriate representation of the word 'bank' in the sentence 'I arrived at the bank after crossing the...' requires knowing if the sentence ends in '... road.' or '... river.'"

"recurrent neural networks have in recent years become the typical network architecture for translation, processing language sequentially in a left-to-right or right-to-left fashion." "In contrast, the Transformer only performs a small, constant number of steps (chosen empirically). In each step, it applies a self-attention mechanism which directly models relationships between all words in a sentence, regardless of their respective position. In the earlier example 'I arrived at the bank after crossing the river', to determine that the word 'bank' refers to the shore of a river and not a financial institution, the Transformer can learn to immediately attend to the word 'river' and make this decision in a single step."
Add a comment...

Post has shared content
"Deep neural networks are more accurate than humans at detecting sexual orientation from facial images." "We used deep neural networks to extract features from 35,326 facial images. " "Given a single facial image, a classifier could correctly distinguish between gay and heterosexual men in 81% of cases, and in 74% of cases for women. Human judges achieved much lower accuracy: 61% for men and 54% for women. The accuracy of the algorithm increased to 91% and 83%, respectively, given five facial images per person."
Add a comment...

Post has attachment
An Entirely New Type of Quantum Computing Has Been Invente
[...]Australian researchers have designed a new type of qubit - the building block of quantum computers - that they say will finally make it possible to manufacture a true, large-scale quantum computer.[...]

Read more: https://goo.gl/vQPg8w
Add a comment...
Wait while more posts are being loaded