Having a lot of text documents (in natural language, unstructured), what are the possible ways of annotating them with some semantic meta-data? For example, consider a short... moreHaving a lot of text documents (in natural language, unstructured), what are the possible ways of annotating them with some semantic meta-data? For example, consider a short document:I saw the company's manager last day.To be able to extract information from it, it must be annotated with additional data to be less ambiguous. The process of finding such meta-data is not in question, so assume it is done manually. The question is how to store these data in a way that further analysis on it can be done more conveniently/efficiently?A possible approach is to use XML tags (see below), but it seems too verbose, and maybe there are better approaches/guidelines for storing such meta-data on text documents.I saw the company'smanager last day. less
I was wondering if anybody knew where I could obtain dictionaries of positive and negative words. I'm looking into sentiment analysis and this is a crucial part of it.
This question came to my mind while working on 2 projects in AI and ML. What If I'm building a model (e.g. Classification Neural Network,K-NN, .. etc) and this model uses some... moreThis question came to my mind while working on 2 projects in AI and ML. What If I'm building a model (e.g. Classification Neural Network,K-NN, .. etc) and this model uses some function that includes randomness. If I don't fix the seed, then I'm going to get different accuracy results every time I run the algorithm on the same training data. However, If I fix it then some other setting might give better results.
Is averaging a set of accuracies enough to say that the accuracy of this model is xx % ?
I'm not sure If this is the right place to ask such a question/open such a discussion. less
Factually speaking , when you know the skills well enough, no certification is really necessary. But for a beginner, it is a catch-22. No experience without an on-job learning and... moreFactually speaking , when you know the skills well enough, no certification is really necessary. But for a beginner, it is a catch-22. No experience without an on-job learning and no job without learned skills! So certifications are the bridge to some sort of assurance of training of requisite skills.
I wanted to check the connection between 2 words in text analytics in python.currently using NLTK package in python.For example "Text = "There are thousands of types of specific... moreI wanted to check the connection between 2 words in text analytics in python.currently using NLTK package in python.For example "Text = "There are thousands of types of specific networks proposed by researchers as modifications or tweaks to existing models"here if i input as networks and researchers, then i should get output as "Proposed by" or "networks proposed by researchers"
I'm testing Google Cloud ML for speeding up my ML model using Tensorflow.
Unfortunately, it seems like Google Cloud ML is extremely slow. My Mainstream-Level PC is at least 10x... moreI'm testing Google Cloud ML for speeding up my ML model using Tensorflow.
Unfortunately, it seems like Google Cloud ML is extremely slow. My Mainstream-Level PC is at least 10x faster than Google Cloud ML.
I doubt it uses GPU, so I did a test. I modified a sample code to force using GPU.
diff --git a/mnist/trainable/trainer/task.py b/mnist/trainable/trainer/task.py
index 9acb349..a64a11d 100644
--- a/mnist/trainable/trainer/task.py
+++ b/mnist/trainable/trainer/task.py
@@ -131,11 +131,12 @@ def run_training():
images_placeholder, labels_placeholder = placeholder_inputs(
FLAGS.batch_size)
- # Build a Graph that computes predictions from the inference model.
- logits = mnist.inference(images_placeholder, FLAGS.hidden1, FLAGS.hidden2)
+ with tf.device("/gpu:0"):
+ # Build a Graph that computes predictions from the inference model.
+ logits = mnist.inference(images_placeholder, FLAGS.hidden1, FLAGS.hidden2)
- # Add to the Graph the Ops for loss calculation.
- loss =... less
The docs for setting up Google Cloud ML suggest installing Tensorflow version r0.11. I've observed that TensorFlow functions newly available in r0.12 raise exceptions when run on... moreThe docs for setting up Google Cloud ML suggest installing Tensorflow version r0.11. I've observed that TensorFlow functions newly available in r0.12 raise exceptions when run on Cloud ML. Is there a timeline for Cloud ML supporting r0.12? Will switching between r0.11 and r0.12 be optional or mandatory?