AIRLINK 74.00 Decreased By ▼ -0.25 (-0.34%)
BOP 5.14 Increased By ▲ 0.09 (1.78%)
CNERGY 4.55 Increased By ▲ 0.13 (2.94%)
DFML 37.15 Increased By ▲ 1.31 (3.66%)
DGKC 89.90 Increased By ▲ 1.90 (2.16%)
FCCL 22.40 Increased By ▲ 0.20 (0.9%)
FFBL 33.03 Increased By ▲ 0.31 (0.95%)
FFL 9.75 Decreased By ▼ -0.04 (-0.41%)
GGL 10.75 Decreased By ▼ -0.05 (-0.46%)
HBL 115.50 Decreased By ▼ -0.40 (-0.35%)
HUBC 137.10 Increased By ▲ 1.26 (0.93%)
HUMNL 9.95 Increased By ▲ 0.11 (1.12%)
KEL 4.60 Decreased By ▼ -0.01 (-0.22%)
KOSM 4.83 Increased By ▲ 0.17 (3.65%)
MLCF 39.75 Decreased By ▼ -0.13 (-0.33%)
OGDC 138.20 Increased By ▲ 0.30 (0.22%)
PAEL 27.00 Increased By ▲ 0.57 (2.16%)
PIAA 24.24 Decreased By ▼ -2.04 (-7.76%)
PIBTL 6.74 Decreased By ▼ -0.02 (-0.3%)
PPL 123.62 Increased By ▲ 0.72 (0.59%)
PRL 27.40 Increased By ▲ 0.71 (2.66%)
PTC 13.90 Decreased By ▼ -0.10 (-0.71%)
SEARL 61.75 Increased By ▲ 3.05 (5.2%)
SNGP 70.15 Decreased By ▼ -0.25 (-0.36%)
SSGC 10.52 Increased By ▲ 0.16 (1.54%)
TELE 8.57 Increased By ▲ 0.01 (0.12%)
TPLP 11.10 Decreased By ▼ -0.28 (-2.46%)
TRG 64.02 Decreased By ▼ -0.21 (-0.33%)
UNITY 26.76 Increased By ▲ 0.71 (2.73%)
WTL 1.38 No Change ▼ 0.00 (0%)
BR100 7,874 Increased By 36.2 (0.46%)
BR30 25,596 Increased By 136 (0.53%)
KSE100 75,342 Increased By 411.7 (0.55%)
KSE30 24,214 Increased By 68.6 (0.28%)
Technology

AI Software offering new doors into your perception

New technology innovations show that scientists can now interpret what a person is able to see, remember, imagine or
Published June 2, 2017

New technology innovations show that scientists can now interpret what a person is able to see, remember, imagine or dream.

In order to decode and predict a person’s imagination, researchers from Kyoto and ATR (Advanced Telecommunications Research) Computational Neuroscience Laboratories University, made use of neural network-based artificial intelligence.

Huffington Post reported Yukiyasu Kamitani, the team leader, stated, “When we gaze at an object, our brains process these patterns hierarchically, starting with the simplest and progressing to more complex features.”

Explaining about the AI software, he said, “The AI we used works on the same principle. Named 'Deep Neural Network', or DNN, it was trained by a group now at Google.”

The results published in Nature Communications showed that the DNN can decode the activity of brain patterns into signal patterns of stimulated neurons when both are shown the similar image.

Apart from that, the researchers also discovered that the higher and lower visual brain areas can better decode respective layers of the DNN which in turn reveals a homology between the neural network and the human brain.

“We tested whether a DNN signal pattern decoded from brain activity can be used to identify seen or imagined objects from arbitrary categories. The decoder takes neural network patterns and compares these with image data from a large database. Sure enough, the decoder could identify target objects with high probability,” described Kamitani.

According to Science Daily, Kamitani further wishes to advance the precision of image identification of their discovery. “Bringing AI research and brain science closer together could open the door to new brain-machine interfaces, perhaps even bringing us closer to understanding consciousness itself,” he concluded.

Copyright Business Recorder, 2017

Comments

Comments are closed.