Difference between revisions of "Class"
m |
|||
| (3 intermediate revisions by the same user not shown) | |||
| Line 1: | Line 1: | ||
| + | {{#seo: | ||
| + | |title=PRIMO.ai | ||
| + | |titlemode=append | ||
| + | |keywords=artificial, intelligence, machine, learning, models, algorithms, data, singularity, moonshot, Tensorflow, Google, Nvidia, Microsoft, Azure, Amazon, AWS | ||
| + | |description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools | ||
| + | }} | ||
https://courses.nvidia.com/dashboard | https://courses.nvidia.com/dashboard | ||
| + | |||
| + | * [https://www.google.com/search?q=Yuval+Mazor+%40nividia.com&oq=Yuval+Mazor+%40nividia.com&aqs=chrome..69i57j69i58.9126j0j8&sourceid=chrome&ie=UTF-8 Yuval Mazor | NVIDIA] | ||
Jupyer notebooks: Shift+Enter to run cell | Jupyer notebooks: Shift+Enter to run cell | ||
| Line 11: | Line 19: | ||
*recursion | *recursion | ||
| − | = Word | + | = Word [[Embedding]]s = |
* HMMS, CRF, PGMs | * HMMS, CRF, PGMs | ||
| Line 22: | Line 30: | ||
| − | *Firth 1957 Distributional | + | *Firth 1957 Distributional Hypotheses |
* Word Cloud | * Word Cloud | ||
| − | + | ** Text Classification | |
| − | + | ** Text/Machine Translation (MNT) | |
| − | |||
= Financial News = | = Financial News = | ||
| − | |||
| − | |||
| − | |||
| − | |||
Tools: | Tools: | ||
| Line 45: | Line 48: | ||
Multi-channel LSTM Network | Multi-channel LSTM Network | ||
Keras wih TensorFlow | Keras wih TensorFlow | ||
| − | Utilize the GloVe and FastText Skipgram pretrained | + | Utilize the GloVe and FastText Skipgram pretrained [[embedding]]s, allows he underlying network to access larger feature space to build complex features on top of. |
| − | Can use utilize combinations of various corpus and embedding methods for better performance | + | Can use utilize combinations of various corpus and [[embedding]] methods for better performance |
| − | Bidirectional LSTM network is used o encode sequential information on the embedding layers. | + | Bidirectional LSTM network is used o encode sequential information on the [[embedding]] layers. |
| − | Dense layer to project | + | Dense layer to project final output classification |
| − | Use embedding... | + | Use [[embedding]]... |
| − | + | [[embedding]]s = transfer learning | |
? CNN vs BI-LSTM (RNN) this approach, BI-LSTM does not need a lot of data | ? CNN vs BI-LSTM (RNN) this approach, BI-LSTM does not need a lot of data | ||
| Line 61: | Line 64: | ||
... not a fixed vector size | ... not a fixed vector size | ||
| − | * [ | + | * [https://nlp.stanford.edu/projects/glove/ GloVe] |
| − | * [ | + | * [https://fasttext.cc/ Fasttext] |
| − | * [ | + | * [https://www.slideshare.net/chartbeat/mockup-infographicv4-27900399 News articles per day] |
| − | * [ | + | * [https://github.com/philipperemy/financial-news-dataset News data source] |
| − | * [ | + | * [https://www.analyticsvidhya.com/blog/2017/06/word-embeddings-count-word2veec/ Word embeddings] |
| − | * [ | + | * [https://en.wikipedia.org/wiki/Natural-language_processing Natural Language Processing] |
| − | * [ | + | * [https://en.wikipedia.org/wiki/Sentiment_analysis Sentiment Analysis] |
= Deep Autoencoders for Anomaly Detection = | = Deep Autoencoders for Anomaly Detection = | ||
| − | Variable | + | Variable Autoencoders |
* clustering - latent layers may tell you what number of clusters | * clustering - latent layers may tell you what number of clusters | ||
Latest revision as of 19:07, 26 June 2023
https://courses.nvidia.com/dashboard
Jupyer notebooks: Shift+Enter to run cell
Linguistic Concepts
- conference - anaphors
- gang of four design
- null subject
- recursion
Contents
Word Embeddings
- HMMS, CRF, PGMs
- CBoW -Bag of Words / ngrams - feature per word/n items
- 1-hot Sparse input - create a vector the size of the entire vocabulary
- Stop Words
- TF-IDF
Word2Vec
Skip-Gram
- Firth 1957 Distributional Hypotheses
- Word Cloud
- Text Classification
- Text/Machine Translation (MNT)
Financial News
Tools:
- Glove
- dot product
- FastText
- Skipgram
- Continuous bag of words
Multi-channel LSTM Network Keras wih TensorFlow Utilize the GloVe and FastText Skipgram pretrained embeddings, allows he underlying network to access larger feature space to build complex features on top of.
Can use utilize combinations of various corpus and embedding methods for better performance
Bidirectional LSTM network is used o encode sequential information on the embedding layers.
Dense layer to project final output classification
Use embedding... embeddings = transfer learning
? CNN vs BI-LSTM (RNN) this approach, BI-LSTM does not need a lot of data
Attention mechanism -- translate ... you can look back
... not a fixed vector size
- GloVe
- Fasttext
- News articles per day
- News data source
- Word embeddings
- Natural Language Processing
- Sentiment Analysis
Deep Autoencoders for Anomaly Detection
Variable Autoencoders
- clustering - latent layers may tell you what number of clusters
- anomaly detection
https://courses.nvidia.com/courses/course-v1:DLI+L-FI-06+V1/info
PCA or TSenee
Statistical Arbitrage
arbitrage - monies, stocks (price is better than it should be - fair market value) how right, or how rich? Mean inversion Autoencoder learn the fair market value, then feed in current value
reconstruction error is a signal - just one signal, consider a basket of signals
backtesting - if we run this on previous historical events how well does our algorithm work? (don't use training data !!)
Using Pandas... ori_dataset_categ_transformed.head(10) for i, val in enumerate(list(ori_dataset_categ_transformed.iloc[1])):
if val is 1:
print("Got 1 at {}".format(i))
