SlideShare uma empresa Scribd logo
1 de 40
INFINITE AI
About Us
Abzooba is an Artificial Intelligence (AI) company. We partner with
enterprises in their cognitive journey to augment digital
transformation
Headquartered in Silicon Valley (USA),
with delivery centres in Kolkata & Pune
(India)
200+ Employees
We use xpresso.ai, a set of internal accelerators and
toolkits, to deliver custom built AI and ML solutions
to our customers
Service Offerings Overview
Big Data and Cloud
Collecting and processing of data for
ingestion
Data Science
Deep Learning, Computer Vision and NLP
to solve business problems
Building enterprise-class infrastructure for
seamless AI integration
Lightning fast data processing and real-time insight
provision through distributed processing
Structured and unstructured data ingestion
through a scalable data lake
Expertise in the state-of-the-art Big Data and data
preprocessing tools
Supervised and unsupervised ML algorithms to
solve industry-specific use cases
Creating an efficient ecosystem through natural
language understanding
Deep learning-based computer vision algorithms
to gather insight from images
Ability to process large volume of data using
parallel processing
Deployment of AI solutions in production using
DevOps framework
AI Ops
Integrated Development, Deployment and
Management infrastructure
Index
1. Problem Statement
2. Naïve Solution
3. Word Embedding
4. Recurrent Neural Network
5. Ensemble & Evaluation
6. Hands On
Problem Statement
www.abzooba.co
A Recurrent Neural Pipeline
Build a Recommendation System, that can recommend Technology
Domains & Tags for questions posted on Stack overflow.
Given a question in Stack-Overflow, predict the Technology Domain
& Associated Tags for it.
Multi Class |
Multi Label Document
Politics
Election
Budget
Ban
Entertainment
Concert
Movies
Games
Player
Selection
Classification into multiple-classes
which are independent & Labels
which are not mutually exclusive in
a hierarchical manner.
Question
Dev Ops
Jenkins
AWS
Docker
QA
Testing
Selenium
Big Data
Hadoop
Apache Spark
Haskell
www.abzooba.co
Business Requirements
PRECISION-RECALL
TRADEOFF
NEW METRICS INFERENCE TIME FREQUENCY OF
RELEASE
www.abzooba.co
Understand
Dataset
www.abzooba.co
Understand Data Sourcing
• How was the data collected
• Biased data-collection technique
• Complete or subset of original
data
• Data bias due to the problem or
not ?
Understand Data Behavior
• Word-Character Distribution
• Time based Distribution
• Class/Label DistributionExploratory
Data
Analysis
www.abzooba.co
EDA
Summary
Group Group Name
1 Programming
2 MS-Development Environment
3 Server-Side Development
4 Mobile App Development
5 Dev Environment
6 Front-end/Designing
7 Dynamic UI
8 MVC
9 Dev Ops
10 Big Data
11 QA
12 Project Management
13 Scripting
14 Business Analytics
www.abzooba.co
Naive Approach
www.abzooba.co
Machine Learning with Bag of Words
Master Vocabulary
• Of all the words present in the document
Create
Words with Numbers
• Based on Index in the Vocabulary
Replace
To ML Model
• Document-Label Pair to model
Feed
www.abzooba.co
Words with Numbers
• Based on Index in the Vocabulary
Replace
Notes
• Frequency count based.
• Term frequency–Inverse document frequency.
• Sequence of words not conserved.
www.abzooba.co
To ML Model
• Document-Label Pair to model
Feed
We use a One v/s Rest strategy to learn a classifier for each Tag
www.abzooba.co
Problems
Lack of context &
understanding
Biasness towards certain words
www.abzooba.co
Word Embeddings
www.abzooba.co
What are
Word
Embedding?
Frequency based Embedding
• Count Vector
• TF-IDF Vector
• Co-Occurrence Vector
Prediction based Embedding
• CBOW (Continuous Bag of
words)
• Skip – Gram model
• Transformers acrhitecture are
leading the research front
Word embeddings are feature learning techniques in NLP where
words or phrases from the vocabulary are mapped to vectors of
real numbers.
www.abzooba.co
Why do we need them?
ML algorithms and almost all Deep Learning Architectures are
incapable of processing strings or plain text in their raw form.
To represent human understandable language to binary machine
codes
Better representation leads to better machine understanding
Pipeline
www.abzooba.co
Word
Embedding Data
Pre-processing
Text
Bag of Word
SOTA
Embeddings
Custom
Embeddings
www.abzooba.co
Data
Preparation
Data
Pre-processing
Text
Training
Format
Single Dataset Single Model
Multiple
Dataset
Standard
Division
Model Forest
Normalised
Division
Model Forest
www.abzooba.co
Neural
Networks
www.abzooba.co
Why
Recurrent
Neural
Network
Preserving context of
documents
Sequence of paragraphs &
contents matters
www.abzooba.co
Recurrent Neural
Network
• Every word is an input at a time-step
• Hidden State from previous time-step
www.abzooba.co
Backpropagation
Through Time
• Seq-Vec : Gradients from the last-step is propagated
• Seq-Seq : Gradient at each time-step is propagated
www.abzooba.co
RNN Cell
www.abzooba.co
Parameters
1. word_embeddings: The Embeddings that we want to stack
2. hidden_size : Sequence Length for rolling over time
3. rnn_layers : Number of RNN cells to be stack. Decides how deep the network is
4. bidirectional : Decides whether the models reads the sequence from Left/Right/Both
5. reproject_words : Decides whether we want to retune the word embeddings
6. reproject_words_dimension : Embedding dimension after retuning.
7. dropout : Dropout to be used
8. rnn_type : Type of RNN Cell to be used
www.abzooba.co
Challenges with RNN
• Sensitive to lr & batch size
• Training Loss unstable
• Hard to Train
• Early stopping may lead to dumb model
•High patience level
• Need to train for longer
• Seq-Seq are better than Seq-Vec
Single Model Question
Jenkins
AWS
Docker
Testing
Selenium
Hadoop
Apache Spark
Haskell
www.abzooba.co
Our Model
• Stacked Document Embeddings.
• Multiple Pre-trained and custom trained(by us) word
embeddings stacked.
• Enables capturing different relations & features in the
document.
• Project the embedding to a trainable embedding layer.
Enables fine-tuning for down-stream/explicit task.
• Model
• LSTM
• 2 Layers
• 64Hidden Items (Rolling over time)
• 256 dimension embedding reprojection
www.abzooba.co
Ensembled
Neural Networks
Multi Class |
Multi Label
Question
Dev Ops
Jenkins
AWS
Docker
QA
Testing
Selenium
Big Data
Hadoop
Apache Spark
Haskell
www.abzooba.co
Re-Designed
Model
• Improved Average Coverage by 17% by just changing to
Ensembled models.
• Trade-off with inference time & memory utilization.
• Possible expansion to ensembling on each category.
• Business Impact :
• Slower Inference
• Scalable Training
• Scalable to more domains
www.abzooba.co
Re-Designed
Model
• Ensembled Model of Categories
• Helped in Class imbalance. Alternative to
Bootstrapping.
• Flexibility to set Threshold.
• Flexibility for Hyper Parameter tuning differently.
• Negative Sampling for different classifiers.
www.abzooba.co
Take Away
Recurrent Neural Networks
needs to be trained cautisouly.
Single Deep Learning Models are
not a silver bullet solution to
problems.
Ensemble Models can be used to
sub-divide the problems and
reduce complexity.
Case-sensitivity in models and
embeddings are important factors
to be taken into consideration.
Data augmentation/extrapolation
leads to increased False Positive
apart from generalizing the
model.
www.abzooba.co
Questions
www.abzooba.co
Contact
Amit Agarwal
• Email : amit.agarwal@abzooba.com
• GitHub : https://github.com/amitbcp
• LinkedIn: https://www.linkedin.com/in/amitagarwal6/
Ishant Wankhede
• Email : ishant.wankhede@abzooba.com
• GitHub : https://github.com/IshantWankhede
• LinkedIn: https://www.linkedin.com/in/ishantwankhede/
Thank You

Mais conteúdo relacionado

Mais procurados

Mais procurados (20)

Transformer Introduction (Seminar Material)
Transformer Introduction (Seminar Material)Transformer Introduction (Seminar Material)
Transformer Introduction (Seminar Material)
 
Word embeddings, RNN, GRU and LSTM
Word embeddings, RNN, GRU and LSTMWord embeddings, RNN, GRU and LSTM
Word embeddings, RNN, GRU and LSTM
 
Attention Is All You Need
Attention Is All You NeedAttention Is All You Need
Attention Is All You Need
 
Word2Vec
Word2VecWord2Vec
Word2Vec
 
Introduction to Transformers for NLP - Olga Petrova
Introduction to Transformers for NLP - Olga PetrovaIntroduction to Transformers for NLP - Olga Petrova
Introduction to Transformers for NLP - Olga Petrova
 
Faster R-CNN: Towards real-time object detection with region proposal network...
Faster R-CNN: Towards real-time object detection with region proposal network...Faster R-CNN: Towards real-time object detection with region proposal network...
Faster R-CNN: Towards real-time object detection with region proposal network...
 
Attention Mechanism in Language Understanding and its Applications
Attention Mechanism in Language Understanding and its ApplicationsAttention Mechanism in Language Understanding and its Applications
Attention Mechanism in Language Understanding and its Applications
 
Introduction to Transformer Model
Introduction to Transformer ModelIntroduction to Transformer Model
Introduction to Transformer Model
 
What is word2vec?
What is word2vec?What is word2vec?
What is word2vec?
 
Back propagation
Back propagation Back propagation
Back propagation
 
PR-302: NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
PR-302: NeRF: Representing Scenes as Neural Radiance Fields for View SynthesisPR-302: NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
PR-302: NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
 
Natural language processing and transformer models
Natural language processing and transformer modelsNatural language processing and transformer models
Natural language processing and transformer models
 
Classifying Text using CNN
Classifying Text using CNNClassifying Text using CNN
Classifying Text using CNN
 
Temporal difference learning
Temporal difference learningTemporal difference learning
Temporal difference learning
 
Recurrent Neural Networks, LSTM and GRU
Recurrent Neural Networks, LSTM and GRURecurrent Neural Networks, LSTM and GRU
Recurrent Neural Networks, LSTM and GRU
 
Deep Belief Networks
Deep Belief NetworksDeep Belief Networks
Deep Belief Networks
 
Faster R-CNN - PR012
Faster R-CNN - PR012Faster R-CNN - PR012
Faster R-CNN - PR012
 
오토인코더의 모든 것
오토인코더의 모든 것오토인코더의 모든 것
오토인코더의 모든 것
 
Machine learning clustering
Machine learning clusteringMachine learning clustering
Machine learning clustering
 
Deep learning for NLP and Transformer
 Deep learning for NLP  and Transformer Deep learning for NLP  and Transformer
Deep learning for NLP and Transformer
 

Semelhante a Recurrent Neural Network : Multi-Class & Multi Label Text Classification

Hadoop at Meebo: Lessons in the Real World
Hadoop at Meebo: Lessons in the Real WorldHadoop at Meebo: Lessons in the Real World
Hadoop at Meebo: Lessons in the Real World
voberoi
 

Semelhante a Recurrent Neural Network : Multi-Class & Multi Label Text Classification (20)

javr
javrjavr
javr
 
Venkata
VenkataVenkata
Venkata
 
NLP and Deep Learning for non_experts
NLP and Deep Learning for non_expertsNLP and Deep Learning for non_experts
NLP and Deep Learning for non_experts
 
Global AI Bootcamp Madrid - Azure Databricks
Global AI Bootcamp Madrid - Azure DatabricksGlobal AI Bootcamp Madrid - Azure Databricks
Global AI Bootcamp Madrid - Azure Databricks
 
Ai & Data Analytics 2018 - Azure Databricks for data scientist
Ai & Data Analytics 2018 - Azure Databricks for data scientistAi & Data Analytics 2018 - Azure Databricks for data scientist
Ai & Data Analytics 2018 - Azure Databricks for data scientist
 
Apache Drill (ver. 0.2)
Apache Drill (ver. 0.2)Apache Drill (ver. 0.2)
Apache Drill (ver. 0.2)
 
Global Azure Bootcamp Montreal 2017
Global Azure Bootcamp Montreal 2017Global Azure Bootcamp Montreal 2017
Global Azure Bootcamp Montreal 2017
 
Introduction to Designing and Building Big Data Applications
Introduction to Designing and Building Big Data ApplicationsIntroduction to Designing and Building Big Data Applications
Introduction to Designing and Building Big Data Applications
 
Machine Learning and AI
Machine Learning and AIMachine Learning and AI
Machine Learning and AI
 
Keras Tutorial For Beginners | Creating Deep Learning Models Using Keras In P...
Keras Tutorial For Beginners | Creating Deep Learning Models Using Keras In P...Keras Tutorial For Beginners | Creating Deep Learning Models Using Keras In P...
Keras Tutorial For Beginners | Creating Deep Learning Models Using Keras In P...
 
Writing Code to Work Against any Salesforce Object
Writing Code to Work Against any Salesforce ObjectWriting Code to Work Against any Salesforce Object
Writing Code to Work Against any Salesforce Object
 
Machine Learning on Google Cloud with H2O
Machine Learning on Google Cloud with H2OMachine Learning on Google Cloud with H2O
Machine Learning on Google Cloud with H2O
 
Ssas dmx ile kurum içi verilerin i̇şlenmesi
Ssas dmx ile kurum içi verilerin i̇şlenmesiSsas dmx ile kurum içi verilerin i̇şlenmesi
Ssas dmx ile kurum içi verilerin i̇şlenmesi
 
Leveraging NLP and Deep Learning for Document Recommendations in the Cloud
Leveraging NLP and Deep Learning for Document Recommendations in the CloudLeveraging NLP and Deep Learning for Document Recommendations in the Cloud
Leveraging NLP and Deep Learning for Document Recommendations in the Cloud
 
Big Data Adavnced Analytics on Microsoft Azure
Big Data Adavnced Analytics on Microsoft AzureBig Data Adavnced Analytics on Microsoft Azure
Big Data Adavnced Analytics on Microsoft Azure
 
TechDayPakistan-Slides RAG with Cosmos DB.pptx
TechDayPakistan-Slides RAG with Cosmos DB.pptxTechDayPakistan-Slides RAG with Cosmos DB.pptx
TechDayPakistan-Slides RAG with Cosmos DB.pptx
 
Initiate Edinburgh 2019 - Big Data Meets AI
Initiate Edinburgh 2019 - Big Data Meets AIInitiate Edinburgh 2019 - Big Data Meets AI
Initiate Edinburgh 2019 - Big Data Meets AI
 
Using SparkML to Power a DSaaS (Data Science as a Service): Spark Summit East...
Using SparkML to Power a DSaaS (Data Science as a Service): Spark Summit East...Using SparkML to Power a DSaaS (Data Science as a Service): Spark Summit East...
Using SparkML to Power a DSaaS (Data Science as a Service): Spark Summit East...
 
963
963963
963
 
Hadoop at Meebo: Lessons in the Real World
Hadoop at Meebo: Lessons in the Real WorldHadoop at Meebo: Lessons in the Real World
Hadoop at Meebo: Lessons in the Real World
 

Último

Exploratory Data Analysis - Dilip S.pptx
Exploratory Data Analysis - Dilip S.pptxExploratory Data Analysis - Dilip S.pptx
Exploratory Data Analysis - Dilip S.pptx
DilipVasan
 
1:1原版定制利物浦大学毕业证(Liverpool毕业证)成绩单学位证书留信学历认证
1:1原版定制利物浦大学毕业证(Liverpool毕业证)成绩单学位证书留信学历认证1:1原版定制利物浦大学毕业证(Liverpool毕业证)成绩单学位证书留信学历认证
1:1原版定制利物浦大学毕业证(Liverpool毕业证)成绩单学位证书留信学历认证
ppy8zfkfm
 
Audience Researchndfhcvnfgvgbhujhgfv.pptx
Audience Researchndfhcvnfgvgbhujhgfv.pptxAudience Researchndfhcvnfgvgbhujhgfv.pptx
Audience Researchndfhcvnfgvgbhujhgfv.pptx
Stephen266013
 
Toko Jual Viagra Asli Di Salatiga 081229400522 Obat Kuat Viagra
Toko Jual Viagra Asli Di Salatiga 081229400522 Obat Kuat ViagraToko Jual Viagra Asli Di Salatiga 081229400522 Obat Kuat Viagra
Toko Jual Viagra Asli Di Salatiga 081229400522 Obat Kuat Viagra
adet6151
 
Fuzzy Sets decision making under information of uncertainty
Fuzzy Sets decision making under information of uncertaintyFuzzy Sets decision making under information of uncertainty
Fuzzy Sets decision making under information of uncertainty
RafigAliyev2
 
如何办理新加坡国立大学毕业证(NUS毕业证)学位证成绩单原版一比一
如何办理新加坡国立大学毕业证(NUS毕业证)学位证成绩单原版一比一如何办理新加坡国立大学毕业证(NUS毕业证)学位证成绩单原版一比一
如何办理新加坡国立大学毕业证(NUS毕业证)学位证成绩单原版一比一
hwhqz6r1y
 
一比一原版西悉尼大学毕业证成绩单如何办理
一比一原版西悉尼大学毕业证成绩单如何办理一比一原版西悉尼大学毕业证成绩单如何办理
一比一原版西悉尼大学毕业证成绩单如何办理
pyhepag
 

Último (20)

Exploratory Data Analysis - Dilip S.pptx
Exploratory Data Analysis - Dilip S.pptxExploratory Data Analysis - Dilip S.pptx
Exploratory Data Analysis - Dilip S.pptx
 
How I opened a fake bank account and didn't go to prison
How I opened a fake bank account and didn't go to prisonHow I opened a fake bank account and didn't go to prison
How I opened a fake bank account and didn't go to prison
 
1:1原版定制利物浦大学毕业证(Liverpool毕业证)成绩单学位证书留信学历认证
1:1原版定制利物浦大学毕业证(Liverpool毕业证)成绩单学位证书留信学历认证1:1原版定制利物浦大学毕业证(Liverpool毕业证)成绩单学位证书留信学历认证
1:1原版定制利物浦大学毕业证(Liverpool毕业证)成绩单学位证书留信学历认证
 
AI Imagen for data-storytelling Infographics.pdf
AI Imagen for data-storytelling Infographics.pdfAI Imagen for data-storytelling Infographics.pdf
AI Imagen for data-storytelling Infographics.pdf
 
Atlantic Grupa Case Study (Mintec Data AI)
Atlantic Grupa Case Study (Mintec Data AI)Atlantic Grupa Case Study (Mintec Data AI)
Atlantic Grupa Case Study (Mintec Data AI)
 
Easy and simple project file on mp online
Easy and simple project file on mp onlineEasy and simple project file on mp online
Easy and simple project file on mp online
 
basics of data science with application areas.pdf
basics of data science with application areas.pdfbasics of data science with application areas.pdf
basics of data science with application areas.pdf
 
Audience Researchndfhcvnfgvgbhujhgfv.pptx
Audience Researchndfhcvnfgvgbhujhgfv.pptxAudience Researchndfhcvnfgvgbhujhgfv.pptx
Audience Researchndfhcvnfgvgbhujhgfv.pptx
 
社内勉強会資料  Mamba - A new era or ephemeral
社内勉強会資料   Mamba - A new era or ephemeral社内勉強会資料   Mamba - A new era or ephemeral
社内勉強会資料  Mamba - A new era or ephemeral
 
Data Visualization Exploring and Explaining with Data 1st Edition by Camm sol...
Data Visualization Exploring and Explaining with Data 1st Edition by Camm sol...Data Visualization Exploring and Explaining with Data 1st Edition by Camm sol...
Data Visualization Exploring and Explaining with Data 1st Edition by Camm sol...
 
Toko Jual Viagra Asli Di Salatiga 081229400522 Obat Kuat Viagra
Toko Jual Viagra Asli Di Salatiga 081229400522 Obat Kuat ViagraToko Jual Viagra Asli Di Salatiga 081229400522 Obat Kuat Viagra
Toko Jual Viagra Asli Di Salatiga 081229400522 Obat Kuat Viagra
 
Fuzzy Sets decision making under information of uncertainty
Fuzzy Sets decision making under information of uncertaintyFuzzy Sets decision making under information of uncertainty
Fuzzy Sets decision making under information of uncertainty
 
Pre-ProductionImproveddsfjgndflghtgg.pptx
Pre-ProductionImproveddsfjgndflghtgg.pptxPre-ProductionImproveddsfjgndflghtgg.pptx
Pre-ProductionImproveddsfjgndflghtgg.pptx
 
Generative AI for Trailblazers_ Unlock the Future of AI.pdf
Generative AI for Trailblazers_ Unlock the Future of AI.pdfGenerative AI for Trailblazers_ Unlock the Future of AI.pdf
Generative AI for Trailblazers_ Unlock the Future of AI.pdf
 
2024 Q2 Orange County (CA) Tableau User Group Meeting
2024 Q2 Orange County (CA) Tableau User Group Meeting2024 Q2 Orange County (CA) Tableau User Group Meeting
2024 Q2 Orange County (CA) Tableau User Group Meeting
 
如何办理新加坡国立大学毕业证(NUS毕业证)学位证成绩单原版一比一
如何办理新加坡国立大学毕业证(NUS毕业证)学位证成绩单原版一比一如何办理新加坡国立大学毕业证(NUS毕业证)学位证成绩单原版一比一
如何办理新加坡国立大学毕业证(NUS毕业证)学位证成绩单原版一比一
 
一比一原版西悉尼大学毕业证成绩单如何办理
一比一原版西悉尼大学毕业证成绩单如何办理一比一原版西悉尼大学毕业证成绩单如何办理
一比一原版西悉尼大学毕业证成绩单如何办理
 
Machine Learning for Accident Severity Prediction
Machine Learning for Accident Severity PredictionMachine Learning for Accident Severity Prediction
Machine Learning for Accident Severity Prediction
 
ℂall Girls Balbir Nagar ℂall Now Chhaya ☎ 9899900591 WhatsApp Number 24/7
ℂall Girls Balbir Nagar ℂall Now Chhaya ☎ 9899900591 WhatsApp  Number 24/7ℂall Girls Balbir Nagar ℂall Now Chhaya ☎ 9899900591 WhatsApp  Number 24/7
ℂall Girls Balbir Nagar ℂall Now Chhaya ☎ 9899900591 WhatsApp Number 24/7
 
ℂall Girls Kashmiri Gate ℂall Now Chhaya ☎ 9899900591 WhatsApp Number 24/7
ℂall Girls Kashmiri Gate ℂall Now Chhaya ☎ 9899900591 WhatsApp  Number 24/7ℂall Girls Kashmiri Gate ℂall Now Chhaya ☎ 9899900591 WhatsApp  Number 24/7
ℂall Girls Kashmiri Gate ℂall Now Chhaya ☎ 9899900591 WhatsApp Number 24/7
 

Recurrent Neural Network : Multi-Class & Multi Label Text Classification