power <- function(a,b) { c <- a^b # known function return(c) } power(1,3)
## 1
power(2,3)
## 8
power(3,4)
## 81
What if we don’t know what function to apply, but we have a lot of examples?
func(2)
## 2.895133
func(1)
## 1.666248
func(6)
## 6.399109
Machine learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed.
## ## Attaching package: 'matrixStats'
## The following object is masked from 'package:plyr': ## ## count
calories | protein | fat | sodium | fiber | rating |
---|---|---|---|---|---|
70 | 4 | 1 | 130 | 10.0 | 68 |
120 | 3 | 5 | 15 | 2.0 | 34 |
70 | 4 | 1 | 260 | 9.0 | 59 |
50 | 4 | 0 | 140 | 14.0 | 94 |
110 | 2 | 2 | 180 | 1.5 | 30 |
calories | protein | fat | sodium | fiber | rating | pred_rating |
---|---|---|---|---|---|---|
120 | 3 | 5 | 15 | 2.0 | 34 | 31 |
70 | 4 | 1 | 260 | 9.0 | 59 | 70 |
110 | 2 | 2 | 180 | 1.5 | 30 | 34 |
90 | 2 | 1 | 200 | 4.0 | 49 | 47 |
120 | 1 | 2 | 220 | 0.0 | 18 | 22 |
calories | protein | fat | sodium | fiber | rating | pred_rating |
---|---|---|---|---|---|---|
120 | 3 | 5 | 15 | 2.0 | 34 | 34 |
70 | 4 | 1 | 260 | 9.0 | 59 | 65 |
110 | 2 | 2 | 180 | 1.5 | 30 | 34 |
90 | 2 | 1 | 200 | 4.0 | 49 | 48 |
120 | 1 | 2 | 220 | 0.0 | 18 | 20 |
Cats are mammals.
Cats are mammals.
w1 w2 w3
cats - are
are - cats
are - mammals
mammals - cats
cats - mammals
Keep values of middle network as embeddings for input word
cat = [0.8874 0.4184 0.9876 0.2662 0.0479 0.5825 0.3993 0.0556 0.1302 0.8568 0.4025 0.5344 0.9492 0.0258 0.7850 0.1779 0.4387 0.9506 0.2799 0.9741 0.4159 0.9542 0.9834 0.1766 0.1999 0.2395 0.8560 0.1893 0.5676 0.2971 0.4173 0.6742 0.6488 0.4010 0.5583 0.4708 0.1981 0.4244 0.7771 0.9306 0.0068 0.3926 0.1718 0.5491 0.2884 0.3237 0.8570 0.2799 0.4225 0.2305]
Keep values of middle network as embeddings for input word
cat = [0.8874 0.4184 0.9876 0.2662 0.0479 0.5825 0.3993 0.0556 0.1302 0.8568]
Keep values of middle network as embeddings for input word
cat = [0.8874 0.4184 0.9876 0.2662 0.0479 0.5825 0.3993 0.0556 0.1302 0.8568]
The Marvelous Mathematics of Computational Linguistics:
King - Man + Woman = Queen
The Marvelous Mathematics of Computational Linguistics:
King - Man + Woman = Queen
How much is Big Data?
Will add:
Fast prototyping.
Machine Learning code templates.
Model Interpretation.
Big Data pipelines.
Workshops and tutorials.
Computer Vision.
Natural Language Processing.
Multi GPU training.
General Deep Learning.
Handle Big Data.
Quick Prototyping.
Other?
https://towardsdatascience.com/a-gentle-introduction-to-neural-networks-series-part-1-2b90b87795bc