FOUR
COLORS FOUR WORDS
" MIT TECHNOLOGY REVIEW"
"SEPTEMBER/OCTOBER 2008"
1. Closer
= lebih dekat
2. Associanting
= bergaul
3. Objects
= benda
4. Analogy
= analogi
5. Imagine
= membayangkan
6. Verbally
= secara lisan
7. Indeed
= memang
8. Machine
= mesin
9. Enough
= cukup
10. Researchers
= peneliti
11. Intelelligence
= intelijen
12. Terrible
= buruk
13. Abstaction
= abstraksi
14. Possible
= mungkin
15. Uniquely
= unik
16. Beyond
= luar
17. Cognitive
= kognitif
18. Scientists
= ilmuan
19. Neural
= saraf
20. Networks
= jaringan
21. Might
= mungkin
22. Amount
= jumlah
23. Built
= dibangun di
24. Ability
= kemampuan
25. Effeciently
= efesien
26. Probably
= mungkin
27. Infants
= bayi
28. Perceiving
= mengamati
29. Visually
= visual
30. Understanding
= paham
RESUME
This is closer to the way children learn, by associating words with objects, relationships, and actions.
Cognitive scientists like MIT’S tenenbanum theorize that important components of the mind are missing from today’s neural networks, no matter how large those networks might be. Humans have the ability to learn very quickly from a relatively small amount ofdataand have built-in ability to model the world in 3-D very efficiently. “language builds on other abilities that are probably more basic, that re present in young infants before they have language : perceiving the world visually, acting on our motor systems, understanding the physics of the world or other agents’ goals,” Tenenbaum says.
If he is right, then it will be difficult to re-create language understanding in machines and AI systems without trying to mimic human learning, mental model building, and psychology
Cognitive scientists like MIT’S tenenbanum theorize that important components of the mind are missing from today’s neural networks, no matter how large those networks might be. Humans have the ability to learn very quickly from a relatively small amount ofdataand have built-in ability to model the world in 3-D very efficiently. “language builds on other abilities that are probably more basic, that re present in young infants before they have language : perceiving the world visually, acting on our motor systems, understanding the physics of the world or other agents’ goals,” Tenenbaum says.
If he is right, then it will be difficult to re-create language understanding in machines and AI systems without trying to mimic human learning, mental model building, and psychology
Tidak ada komentar:
Posting Komentar