deep learning neural networks and ai explained
TRANSCRIPT
![Page 2: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/2.jpg)
Deep Neural Network intuition
Embeddings
Transfer Learning
Tips
Outline
![Page 3: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/3.jpg)
Deep Neural Network omnipresence
https://trends.google.com/trends/explore?date=2008-03-09%202017-04-09&q=artificial%20intelligence,machine%20learning,deep%20learning
![Page 4: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/4.jpg)
Deep Neural Network omnipresence
https://trends.google.com/trends/explore?date=2008-03-09%202017-04-09&q=artificial%20intelligence,machine%20learning,deep%20learning
![Page 5: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/5.jpg)
Deep Neural Network omnipresence
https://trends.google.com/trends/explore?date=2008-03-09%202017-04-09&q=artificial%20intelligence,machine%20learning,deep%20learning
![Page 6: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/6.jpg)
Deep Neural Network omnipresence
https://trends.google.com/trends/explore?date=2008-03-09%202017-04-09&q=artificial%20intelligence,machine%20learning,deep%20learning
![Page 7: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/7.jpg)
… or almost
https://trends.google.com/trends/explore?date=2008-03-09%202017-04-09&q=artificial%20intelligence,machine%20learning,deep%20learning
![Page 8: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/8.jpg)
Applications
http://www.yaronhadad.com/deep-learning-most-amazing-applications/
![Page 9: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/9.jpg)
Human1011 neurons 104 synapses per neuron1016 “operations” / sec250 M neurons per mm3 180,000 km of “wires” 25 Watts
Deep Neural Networks sound coolGPU8x1012 operations / sec 500 Watts 5760 (small) cores $2000
![Page 10: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/10.jpg)
Toy example
Num website visits
Num page visited
Average time on page
Converted?
1 13 55s 1
2 1 141s 1
1 8 10s 0
3 5 127s 0
2 3 18s 0
![Page 11: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/11.jpg)
Toy example
Num website visits
Num page visited
Average time on page
Converted?
1 13 55s 1
2 1 141s 1
1 8 10s 0
3 5 127s 0
2 3 18s 0
“Num website visits” does not seem to influence output
![Page 12: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/12.jpg)
Toy example
Num website visits
Num page visited
Average time on page
Converted?
1 13 55s 1
2 1 141s 1
1 8 10s 0
3 5 127s 0
2 3 18s 0
“Num page visited” above 9 seems to be a good threshold, but even when =1 a person can convert ⇒ no simple threshold
![Page 13: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/13.jpg)
Toy example
Num website visits
Num page visited
Average time on page
Converted?
1 13 55s 1
2 1 141s 1
1 8 10s 0
3 5 127s 0
2 3 18s 0
“Avg time on page” > 128 seems to be a good threshold, but even when =55 a person can convert ⇒ no simple threshold
![Page 14: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/14.jpg)
Toy example
1
13
55
??
Num website visits
Num page visited
Average time on page
User converted?w1=??
w2=??
w3=??
> 0 converted< 0 not converted
multiply
sum
1*w1 + 13*w2 + 55*w3 > 0
![Page 15: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/15.jpg)
Toy example
1
13
55
3.58
Num website visits
Num page visited
Average time on page
User converted?-7.04
0.28
0.12
multiply
sum
> 0 ? YES
![Page 16: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/16.jpg)
Toy example
3
5
127
-3.76
Num website visits
Num page visited
Average time on page
User converted?
multiply
sum
> 0 ? NO
-7.04
0.28
0.12
![Page 17: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/17.jpg)
Toy example
Num website visits
Num page visited
Average time on page
3
5
-7.04
0.28
0.12127
Method #1
Num website visits
Num page visited
Average time on page
3
5
-2.4
0.91
0.013127
Method #2
Num website visits
Num page visited
Average time on page
3
5
-3.9
0.21
0.03127
Method #3
Num website visits
Num page visited
Average time on page
3
5
-1.1
0.83
0.18127
Method #4
![Page 18: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/18.jpg)
Toy example
1
13
55
Method #1
Method #2
Method #3
Method #4
Final estimate
Num website visits
Num page visited
Average time on page
![Page 19: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/19.jpg)
Toy example
1
13
55
Method #1
Method #2
Method #3
Method #4
Final estimate
Num website visits
Num page visited
Average time on page
input layerhidden layer
output layer
![Page 20: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/20.jpg)
Toy example
1
13
55
Method #1
Method #2
Method #3
Method #4
Final estimate
Num website visits
Num page visited
Average time on page
input layerhidden layer
output layer
Deep = lots of hidden layers
![Page 21: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/21.jpg)
http://www.asimovinstitute.org/neural-network-zoo/
Lots of configurations
![Page 22: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/22.jpg)
Open source toolkits
![Page 23: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/23.jpg)
Neural Networks - Take Home Message● Applicable to endless domains: object recognition, medical imaging,
automotive, finance, robotics, natural language processing, translation
systems, speech recognition
● At the simplest levels only a series of nodes doing sums & thresholding
● Lots of variety
● Lots of open source tools
![Page 24: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/24.jpg)
Embeddings
![Page 25: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/25.jpg)
Context: object recognitionAutomatically classify product images into 1000s
of categories
Dress Boot
![Page 26: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/26.jpg)
Image dataset Image Features Classifier
● Edges● Contrast● Local patterns● colors
● Adaboost● SVM● Random
Forests● Neural Network
Image Classifier (old school)
![Page 27: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/27.jpg)
0.2-0.30.150.750.11……
0.93
V =
Input Image Feature extraction Image features
Image Features (old school)
Classifier
f(V) > 0
![Page 28: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/28.jpg)
Image dataset Image Features Classifier
● Edges● Contrast● Local patterns● colors
● Adaboost● SVM● Random
Forests● Neural Network
10% 45% 45%
Effort (old school)
![Page 29: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/29.jpg)
...still in use today
![Page 30: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/30.jpg)
DatasetData gathered from 100s of scraped webshops
![Page 31: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/31.jpg)
Dataset5 million products, uncategorised
![Page 32: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/32.jpg)
Datasetuncategorised
● Keywords filtering
● Visual clustering
● Human inspection
~500 labelled classes~ 1000 images / class
![Page 33: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/33.jpg)
Image classifier (the new way)
Deep Convolutional Neural Network (DCNN)~500 labelled classes~1000 images / class
Backpropagation + Gradient descent
![Page 34: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/34.jpg)
Image classifier (the new way)
Forward passtraining imagelabel: pans
![Page 35: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/35.jpg)
Image classifier (the new way)
Forward passtraining imagelabel: pans
![Page 36: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/36.jpg)
Image classifier (the new way)
Forward passtraining imagelabel: pans
![Page 37: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/37.jpg)
Image classifier (the new way)
Forward passtraining imagelabel: pans
![Page 38: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/38.jpg)
Image classifier (the new way)
Forward passtraining imagelabel: pans
![Page 39: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/39.jpg)
Image classifier (the new way)
Forward passtraining imagelabel: pans
![Page 40: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/40.jpg)
Image classifier (the new way)
Forward passtraining imagelabel: pans
![Page 41: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/41.jpg)
Image classifier (the new way)
Forward passtraining imagelabel: pans
![Page 42: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/42.jpg)
Image classifier (the new way)
Forward passtraining imagelabel: pans
predicted label=shoe
![Page 43: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/43.jpg)
Image classifier (the new way)
training imagelabel: pans
predicted label=shoe
Backpropagation + Gradient descent
![Page 44: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/44.jpg)
Image classifier (the new way)
training imagelabel: pans
predicted label=shoe
Backpropagation + Gradient descent= update weights “towards target”
![Page 45: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/45.jpg)
Image classifier (the new way)
Forward pass
Backpropagation + Gradient descent
● Repeat for all training images
● Repeat till stopping criteria
![Page 46: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/46.jpg)
Effort (the new way)
50% 50%
~500 labelled classes~1000 images / class Deep Convolutional Neural Network (DCNN)
![Page 47: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/47.jpg)
What is going on in the network?
Dress
![Page 48: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/48.jpg)
http://vision03.csail.mit.edu/cnn_art/data/single_layer.png
What is going on in the network?
predicted label=pans
![Page 49: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/49.jpg)
http://vision03.csail.mit.edu/cnn_art/data/single_layer.png
What is going on in the network?
AbstractImage
“concepts”
Low levelImage
“concepts”
![Page 50: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/50.jpg)
Embedding = self-learnt descriptors
Abstract level concept / descriptor
Dress
0.2-0.30.150.750.11……
0.93
![Page 51: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/51.jpg)
Distance in embedding space
E(a), E(b), E(c)
a
b
c
d ( , ) >> d ( , )E(a) E(b) E(c) E(b)
![Page 52: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/52.jpg)
Distance in embedding space
![Page 53: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/53.jpg)
Bracelets (unsorted)
![Page 54: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/54.jpg)
Bracelets (sorted on embedding)
![Page 55: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/55.jpg)
Bracelets (sorted on embedding)
![Page 56: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/56.jpg)
Shoes (unsorted)
![Page 57: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/57.jpg)
Shoes (sorted on embedding)
![Page 58: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/58.jpg)
Shoes (sorted on embedding)
![Page 59: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/59.jpg)
Iterative refinementNewly discovered
classesRe-train classifier Results
95% from 5M products classified with confidence > 96%
More than 250 new labeled categories
![Page 60: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/60.jpg)
Context: identity recognitionAutomatically recognize celebrities from
red carpet events
Jennifer Aniston
LL Cool J
![Page 61: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/61.jpg)
Embedding training
Triplet Loss
Train network to discriminate between triplets of images
Triplets
![Page 62: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/62.jpg)
Training
Random embedding initialization
Embedding training
Trained embedding
![Page 63: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/63.jpg)
Celebrity identifier
![Page 64: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/64.jpg)
Celebrity identifier
![Page 65: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/65.jpg)
Celebrity identifier
![Page 66: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/66.jpg)
Celebrity identifier
![Page 67: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/67.jpg)
Celebrity identifier
![Page 68: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/68.jpg)
NLP - Word embeddings
https://medium.com/@ageitgey/machine-learning-is-fun-part-5-language-translation-with-deep-learning-and-the-magic-of-sequences-2ace0acca0aa
With a different network setup we can learn an embedding for words:
![Page 69: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/69.jpg)
NLP - Word embeddings
Each word is represented by a vector. Vector allow to explore very
interesting relationships learnt automatically from the data:
● King - man + woman → queen
● Paris - France + Italy → Rome
● Obama - USA + Russia → Putin
● President - power → prime minister
![Page 70: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/70.jpg)
Embeddings - Take Home Message● From feature engineering to data collection
● Neural Networks automatically learn relevant high level
abstractions
● Embedding spaces very useful to explore data
● Application areas: retrieval or ranking tasks (e.g. product
recommendation, customer segmentation), classification
![Page 71: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/71.jpg)
Transfer learning
![Page 72: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/72.jpg)
ImageNet
1.5 million training examples
1000 categories
Training time ~ days on best GPUs
![Page 73: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/73.jpg)
Transfer Learningrandomly initialized
weightsImageNet
![Page 74: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/74.jpg)
Transfer Learningrandomly initialized
weightsImageNet Network trained to
classify 1000 classes
Classify correctly (>90%) images in
1000 classes
![Page 75: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/75.jpg)
Transfer LearningNew data
New classes
?
![Page 76: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/76.jpg)
Transfer Learningrandomly initialized
weightsImageNet Network trained to
classify 1000 classesFine-tune model(update weights)
New dataNew classes
![Page 77: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/77.jpg)
Transfer Learningrandomly initialized
weightsImageNet Network trained to
classify 1000 classesFine-tune model(update weights)
New dataNew classes● Faster training time
● Better performance
![Page 78: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/78.jpg)
Sharing pre-trained models● Model-Zoo:
https://github.com/BVLC/caffe/wiki/Model-Zoo
● Common format to share pre-trained models
● Active discussion and contributions
![Page 79: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/79.jpg)
Sharing pre-trained models
![Page 80: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/80.jpg)
Transfer Learning - recommendations
small; similar
large; similar
small; different
large; different
Similarity of the data
Size
of d
atab
ase
![Page 81: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/81.jpg)
Transfer Learning - recommendations
Small; similar
large; similar
small; different
large; different
Use existing embedding
Similarity of the data
Size
of d
atab
ase
![Page 82: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/82.jpg)
Transfer Learning - recommendations
Small; similar
large; similar
small; different
large; different
Use existing embedding
Fine-tune complete network
Similarity of the data
Size
of d
atab
ase
![Page 83: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/83.jpg)
Transfer Learning - recommendations
Small; similar
large; similar
small; different
large; different
Use existing embedding
Fine-tune complete network
Use activations from earlier
in the network
Fine-tune complete network (or start from scratch)
Similarity of the data
Size
of d
atab
ase
![Page 84: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/84.jpg)
Transfer Learning - recommendations
Small; similar
large; similar
small; different
large; different
Use existing embedding
Fine-tune complete network
Use activations from earlier
in the network
Fine-tune complete network (or start from scratch)
Similarity of the data
Size
of d
atab
ase
![Page 85: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/85.jpg)
Transfer Learning - Take Home Message● Faster progress
● Training also with much smaller amount of data
● Check closest available model before starting from scratch
![Page 86: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/86.jpg)
Should we all go
deep?
![Page 87: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/87.jpg)
Some questions you should ask● What is the performance of the baseline?
○ What can be achieved with a simpler system?
○ Can we start testing the value proposition with a simpler system?
![Page 88: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/88.jpg)
Some questions you should ask● What is the performance of the baseline?
● How much training data is required?
![Page 89: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/89.jpg)
Some questions you should ask● What is the performance of the baseline?
● How much training data is required?
● Do we have the data, can we acquire it or how long does it take to collect it?
![Page 90: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/90.jpg)
Some questions you should ask● What is the performance of the baseline?
● How much training data is required?
● Do we have the data, can we acquire it or how long does it take to collect it?
● Do we need labeled data or can we use unlabeled data?
![Page 91: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/91.jpg)
Some questions you should ask● What is the performance of the baseline?
● How much training data is required?
● Do we have the data, can we acquire it or how long does it take to collect it?
● Do we need labeled data or can we use unlabeled data?
● How well does it work on data it has never seen? Generalization / Overfitting
![Page 92: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/92.jpg)
Some questions you should ask● What is the performance of the baseline?
● How much training data is required?
● Do we have the data, can we acquire it or how long does it take to collect it?
● Do we need labeled data or can we use unlabeled data?
● How well does it work on data it has never seen? Generalization / Overfitting
● What are the failure cases?
![Page 93: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/93.jpg)
Some questions you should ask● What is the performance of the baseline?
● How much training data is required?
● Do we have the data, can we acquire it or how long does it take to collect it?
● Do we need labeled data or can we use unlabeled data?
● How well does it work on data it has never seen? Generalization / Overfitting
● What are the failure cases?
● How reliable is the confidence of the prediction?
![Page 94: Deep learning neural networks and AI explained](https://reader031.vdocuments.us/reader031/viewer/2022021814/58ef85191a28ab7b5a8b45fd/html5/thumbnails/94.jpg)
Some questions you should ask● What is the performance of the baseline?
● How much training data is required?
● Do we have the data, can we acquire it or how long does it take to collect it?
● Do we need labeled data or can we use unlabeled data?
● How well does it work on data it has never seen? Generalization / Overfitting
● What are the failure cases?
● How reliable is the confidence of the prediction?
● Can we explain why a prediction has been made?