Class - Revision history

BPeat at 00:07, 27 June 2023

2023-06-27T00:07:47Z

BPeat: Text replacement - "http:" to "https:"

2023-03-28T00:22:46Z

Text replacement - "http:" to "https:"

BPeat at 19:23, 3 February 2019

2019-02-03T19:23:00Z

BPeat at 08:56, 14 November 2018

2018-11-14T08:56:43Z

BPeat at 20:15, 23 October 2018

2018-10-23T20:15:30Z

BPeat at 20:14, 23 October 2018

2018-10-23T20:14:55Z

BPeat at 19:49, 23 October 2018

2018-10-23T19:49:14Z

BPeat at 19:34, 23 October 2018

2018-10-23T19:34:22Z

BPeat at 19:29, 23 October 2018

2018-10-23T19:29:13Z

BPeat at 19:25, 23 October 2018

2018-10-23T19:25:13Z

@@ Line 19: / Line 19: @@
 *recursion
-= Word Embeddings =
+= Word [[Embedding]]s =
 * HMMS, CRF, PGMs
@@ Line 48: / Line 48: @@
 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.
+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 final output classification
-Use embedding...
+Use [[embedding]]...
-embeddings = transfer learning
+[[embedding]]s = transfer learning
 ? CNN vs BI-LSTM (RNN) this approach, BI-LSTM does not need a lot of data

@@ Line 5: / Line 5: @@
 |description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools
 }}
-http://courses.nvidia.com/dashboard
+https://courses.nvidia.com/dashboard
-* [http://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]
+* [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
@@ Line 64: / Line 64: @@
                      ... not a fixed vector size
-* [http://nlp.stanford.edu/projects/glove/ GloVe]
+* [https://nlp.stanford.edu/projects/glove/ GloVe]
-* [http://fasttext.cc/ Fasttext]
+* [https://fasttext.cc/ Fasttext]
-* [http://www.slideshare.net/chartbeat/mockup-infographicv4-27900399 News articles per day]
+* [https://www.slideshare.net/chartbeat/mockup-infographicv4-27900399 News articles per day]
-* [http://github.com/philipperemy/financial-news-dataset News data source]
+* [https://github.com/philipperemy/financial-news-dataset News data source]
-* [http://www.analyticsvidhya.com/blog/2017/06/word-embeddings-count-word2veec/ Word embeddings]
+* [https://www.analyticsvidhya.com/blog/2017/06/word-embeddings-count-word2veec/ Word embeddings]
-* [http://en.wikipedia.org/wiki/Natural-language_processing Natural Language Processing]
+* [https://en.wikipedia.org/wiki/Natural-language_processing Natural Language Processing]
-* [http://en.wikipedia.org/wiki/Sentiment_analysis Sentiment Analysis]
+* [https://en.wikipedia.org/wiki/Sentiment_analysis Sentiment Analysis]
 = Deep Autoencoders for Anomaly Detection =

← Older revision		Revision as of 19:23, 3 February 2019
Line 1:		Line 1:
−	~~https~~://courses.nvidia.com/dashboard	+	{{#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
		+	}}
		+	http://courses.nvidia.com/dashboard

	* [http://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]		* [http://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]

@@ Line 1: / Line 1: @@
 https://courses.nvidia.com/dashboard
 Jupyer notebooks:  Shift+Enter to run cell
@@ Line 22: / Line 24: @@
-*Firth 1957 Distributional Hypothess
+*Firth 1957 Distributional Hypotheses
 * Word Cloud
-= Text Classification =
+** Text Classification
-= Text/Machine Translation (MNT) =
+** Text/Machine Translation (MNT)
 = Financial News =
 Tools:
@@ Line 51: / Line 48: @@
 Bidirectional LSTM network is used o encode sequential information on the embedding layers.
-Dense layer to project fnal output classification
+Dense layer to project final output classification
 Use embedding...
@@ Line 71: / Line 68: @@
 = Deep Autoencoders for Anomaly Detection =
-Variable Auencoders
+Variable Autoencoders
 * clustering - latent layers may tell you what number of clusters

@@ Line 90: / Line 90: @@
 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))

← Older revision		Revision as of 20:14, 23 October 2018
Line 89:		Line 89:

	backtesting - if we run this on previous historical events how well does our algorithm work? (don't use training data !!)		backtesting - if we run this on previous historical events how well does our algorithm work? (don't use training data !!)
		+
		+
		+	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))

← Older revision		Revision as of 19:34, 23 October 2018
Line 82:		Line 82:

	reconstruction error is a signal - just one signal, consider a basket of signals		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 !!)

@@ Line 75: / Line 75: @@
 PCA or TSenee
 Mean inversion
-Statistical Arbitrage
+Autoencoder learn the fair market value, then feed in current value
-Autoecoder learn the fair market value, then feed in current value
+reconstruction error is a signal - just one signal, consider a basket of signals

← Older revision		Revision as of 19:25, 23 October 2018
Line 63:		Line 63:
	* [http://en.wikipedia.org/wiki/Natural-language_processing Natural Language Processing]		* [http://en.wikipedia.org/wiki/Natural-language_processing Natural Language Processing]
	* [http://en.wikipedia.org/wiki/Sentiment_analysis Sentiment Analysis]		* [http://en.wikipedia.org/wiki/Sentiment_analysis Sentiment Analysis]
		+
		+	= Deep Autoencoders for Anomaly Detection =
		+
		+	Variable Auencoders
		+
		+	* 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
		+
		+	Mean inversion
		+	Statistical Arbitrage
		+	arbitrage - monies, stocks (price is better than it should be - fair market value) how right, or how rich?
		+
		+	Autoecoder learn the fair market value, then feed in current value