Title | What if... |
Publication Type | Views & Reviews |
Year of Publication | 2015 |
Authors | Poggio, T |
Date Published | 06/2015 |
Abstract | The background: DCLNs (Deep Convolutional Learning Networks) are doing very wellOver the last 3 years and increasingly so in the last few months, I have seen supervised DCLNs — feedforward and recurrent — do more and more of everything quite well. They seem to learn good representations for a growing number of speech and text problems (for a review by the pioneers in the field see LeCun, Bengio, Hinton, 2015). More interestingly, it is increasingly clear, as I will discuss later, that instead of being trained on millions of labeled examples they can be trained in implicitly supervised ways. This breakthrough in machine learning triggers a few dreams. What if we have now the basic answer to how to develop brain-like intelligence and its basic building blocks?... |
Citation Key | 2062 |
Download:
What if.pdf