R User Group Malaysia Meet Up - Handwritten Recognition using Deep Learning with R
Source code available at: https://github.com/kuanhoong/myRUG_DeepLearning
The policies of urban development and housing in India have come a long way since 1950s. The pressure of urban population and lack of housing and basic services were very much evident in the early 1950s. In some cities this was compounded by migration of people from Pakistan. However, the general perception of the policy makers was that India is pre-dominantly an agricultural and rural economy and that there are potent dangers of over urbanisation which will lead to the drain of resources from the countryside to feed the cities.
The policies of urban development and housing in India have come a long way since 1950s. The pressure of urban population and lack of housing and basic services were very much evident in the early 1950s. In some cities this was compounded by migration of people from Pakistan. However, the general perception of the policy makers was that India is pre-dominantly an agricultural and rural economy and that there are potent dangers of over urbanisation which will lead to the drain of resources from the countryside to feed the cities.
AFDS 2012 Phil Rogers Keynote: THE PROGRAMMER’S GUIDE TO A UNIVERSE OF POSSIB...HSA Foundation
Phil Roger goes deeper into what HSA is, and some of the area it can address since his first presentation on HSA in 2011. He also announces the HSA Foundation and it founding members
AFDS 2011 Phil Rogers Keynote: “The Programmer’s Guide to the APU Galaxy.”HSA Foundation
AFDS Keynote: “The Programmer’s Guide to the APU Galaxy.”
Phil Rogers, AMD Corporate Fellow
It’s a well-understood maxim in the technology industry that software and hardware must evolve in parallel, and be well matched, to achieve greatness. With the introduction of the world’s first APU in January 2011, AMD pointed the world toward a new way of computing. This was very much a first step in an architectural journey that is well underway at AMD. APUs combine different processing engines in single-chip combinations to strike a unique balance between the dimensions of performance, power consumption and price. Hear how AMD is working to ease the programmer’s access to this new level of compute horsepower and dramatically expand the processing resources available to modern applications
Neural Networks in the Wild: Handwriting RecognitionJohn Liu
Demonstration of linear and neural network classification methods for the problem of offline handwriting recognition using the NIST SD19 Dataset. Tutorial on building neural networks in Pylearn2 without YAML. iPython notebook located at nbviewer.ipython.org/github/guard0g/HandwritingRecognition/tree/master/Handwriting%20Recognition%20Workbook.ipynb
Big Data Analytics (ML, DL, AI) hands-onDony Riyanto
Ini adalah slide tambahan dari materi pengenalan Big Data Analytics (di file berikutnya), yang mengajak kita mulai hands-on dengan beberapa hal terkait Machine/Deep Learning, Big Data (batch/streaming), dan AI menggunakan Tensor Flow
Neural Networks, Spark MLlib, Deep LearningAsim Jalis
What are neural networks? How to use the neural networks algorithm in Apache Spark MLlib? What is Deep Learning? Presented at Data Science Meetup at Galvanize on 2/17/2016.
For code see IPython/Jupyter/Toree notebook at http://nbviewer.jupyter.org/gist/asimjalis/4f911882a1ab963859ce
Performance Comparison between Pytorch and Mindsporeijdms
Deep learning has been well used in many fields. However, there is a large amount of data when training neural networks, which makes many deep learning frameworks appear to serve deep learning practitioners, providing services that are more convenient to use and perform better. MindSpore and PyTorch are both deep learning frameworks. MindSpore is owned by HUAWEI, while PyTorch is owned by Facebook. Some people think that HUAWEI's MindSpore has better performance than FaceBook's PyTorch, which makes deep learning practitioners confused about the choice between the two. In this paper, we perform analytical and experimental analysis to reveal the comparison of training speed of MIndSpore and PyTorch on a single GPU. To ensure that our survey is as comprehensive as possible, we carefully selected neural networks in 2 main domains, which cover computer vision and natural language processing (NLP). The contribution of this work is twofold. First, we conduct detailed benchmarking experiments on MindSpore and PyTorch to analyze the reasons for their performance differences. This work provides guidance for end users to choose between these two frameworks.
AFDS 2012 Phil Rogers Keynote: THE PROGRAMMER’S GUIDE TO A UNIVERSE OF POSSIB...HSA Foundation
Phil Roger goes deeper into what HSA is, and some of the area it can address since his first presentation on HSA in 2011. He also announces the HSA Foundation and it founding members
AFDS 2011 Phil Rogers Keynote: “The Programmer’s Guide to the APU Galaxy.”HSA Foundation
AFDS Keynote: “The Programmer’s Guide to the APU Galaxy.”
Phil Rogers, AMD Corporate Fellow
It’s a well-understood maxim in the technology industry that software and hardware must evolve in parallel, and be well matched, to achieve greatness. With the introduction of the world’s first APU in January 2011, AMD pointed the world toward a new way of computing. This was very much a first step in an architectural journey that is well underway at AMD. APUs combine different processing engines in single-chip combinations to strike a unique balance between the dimensions of performance, power consumption and price. Hear how AMD is working to ease the programmer’s access to this new level of compute horsepower and dramatically expand the processing resources available to modern applications
Neural Networks in the Wild: Handwriting RecognitionJohn Liu
Demonstration of linear and neural network classification methods for the problem of offline handwriting recognition using the NIST SD19 Dataset. Tutorial on building neural networks in Pylearn2 without YAML. iPython notebook located at nbviewer.ipython.org/github/guard0g/HandwritingRecognition/tree/master/Handwriting%20Recognition%20Workbook.ipynb
Big Data Analytics (ML, DL, AI) hands-onDony Riyanto
Ini adalah slide tambahan dari materi pengenalan Big Data Analytics (di file berikutnya), yang mengajak kita mulai hands-on dengan beberapa hal terkait Machine/Deep Learning, Big Data (batch/streaming), dan AI menggunakan Tensor Flow
Neural Networks, Spark MLlib, Deep LearningAsim Jalis
What are neural networks? How to use the neural networks algorithm in Apache Spark MLlib? What is Deep Learning? Presented at Data Science Meetup at Galvanize on 2/17/2016.
For code see IPython/Jupyter/Toree notebook at http://nbviewer.jupyter.org/gist/asimjalis/4f911882a1ab963859ce
Performance Comparison between Pytorch and Mindsporeijdms
Deep learning has been well used in many fields. However, there is a large amount of data when training neural networks, which makes many deep learning frameworks appear to serve deep learning practitioners, providing services that are more convenient to use and perform better. MindSpore and PyTorch are both deep learning frameworks. MindSpore is owned by HUAWEI, while PyTorch is owned by Facebook. Some people think that HUAWEI's MindSpore has better performance than FaceBook's PyTorch, which makes deep learning practitioners confused about the choice between the two. In this paper, we perform analytical and experimental analysis to reveal the comparison of training speed of MIndSpore and PyTorch on a single GPU. To ensure that our survey is as comprehensive as possible, we carefully selected neural networks in 2 main domains, which cover computer vision and natural language processing (NLP). The contribution of this work is twofold. First, we conduct detailed benchmarking experiments on MindSpore and PyTorch to analyze the reasons for their performance differences. This work provides guidance for end users to choose between these two frameworks.
Covers basics Artificial neural networks and motivation for deep learning and explains certain deep learning networks, including deep belief networks and autoencoders. It also details challenges of implementing a deep learning network at scale and explains how we have implemented a distributed deep learning network over Spark.
Traditional Machine Learning had used handwritten features and modality-specific machine learning to classify images, text or recognize voices. Deep learning / Neural network identifies features and finds different patterns automatically. Time to build these complex tasks has been drastically reduced and accuracy has exponentially increased because of advancements in Deep learning. Neural networks have been partly inspired from how 86 billion neurons work in a human and become more of a mathematical and a computer problem. We will see by the end of the blog how neural networks can be intuitively understood and implemented as a set of matrix multiplications, cost function, and optimization algorithms.
Hadoop Summit 2014 Distributed Deep LearningAdam Gibson
Deep Learning on Hadoop with DeepLearning4j and Metronome
Deep-learning is useful in detecting anomalies like fraud, spam and money laundering; identifying similarities to augment search and text analytics; predicting customer lifetime value and churn; recognizing faces and voices.
Deeplearning4j is an infinitely scalable deep-learning architecture suitable for Hadoop and other big-data structures. It includes a distributed deep-learning framework and a normal deep-learning framework; i.e. it runs on a single thread as well. Training takes place in the cluster, which means it can process massive amounts of data. Nets are trained in parallel via iterative reduce, and they are equally compatible with Java, Scala and Clojure. The distributed deep-learning framework is made for data input and neural net training at scale, and its output should be highly accurate predictive models.
The framework's neural nets include restricted Boltzmann machines, deep-belief networks, deep autoencoders, convolutional nets and recursive neural tensor networks.
Hadoop Summit 2014 - San Jose - Introduction to Deep Learning on HadoopJosh Patterson
As the data world undergoes its cambrian explosion phase our data tools need to become more advanced to keep pace. Deep Learning has emerged as a key tool in the non-linear arms race of machine learning. In this session we will take a look at how we parallelize Deep Belief Networks in Deep Learning on Hadoop’s next generation YARN framework with Iterative Reduce. We’ll also look at some real world examples of processing data with Deep Learning such as image classification and natural language processing.
Deep Learning libraries and first experiments with TheanoVincenzo Lomonaco
In recent years, neural networks and deep learning techniques have shown to perform well on many
problems in image recognition, speech recognition, natural language processing and many other tasks.
As a result, a large number of libraries, toolkits and frameworks came out in different languages and
with different purposes. In this report, firstly we take a look at these projects and secondly we choose the
framework that best suits our needs: Theano. Eventually, we implement a simple convolutional neural net
using this framework to test both its ease-of-use and efficiency.
Artificial Intelligence (A.I.) is a multidisciplinary field whose goal is to automate
activities that presently require human intelligence. Recent successes in A.I. include
computerized medical diagnosticians and systems that automatically customize
hardware to particular user requirements. The major problem areas addressed in A.I. can
be summarized as Perception, Manipulation, Reasoning, Communication, and Learning.
Perception is concerned with building models of the physical world from sensory input
(visual, audio, etc.). Manipulation is concerned with articulating appendages (e.g.,
mechanical arms, locomotion devices) in order to effect a desired state in the physical
world. Reasoning is concerned with higher level cognitive functions such as planning,
drawing inferential conclusions from a world model, diagnosing, designing, etc.
Communication treats the problem understanding and conveying information through
the use of language. Finally, Learning treats the problem of automatically improving
system performance over time based on the system's experience. Many important
technical concepts have arisen from A.I. that unify these diverse problem areas and that
form the foundation of the scientific discipline. Generally, A.I. systems function based
on a Knowledge Base of facts and rules that characterize the system's domain of
proficiency. The elements of a Knowledge Base consist of independently valid (or at
least plausible) chunks of information. The system must automatically organize and
utilize this information to solve the specific problems that it encounters. This
organization process can be generally characterized as a Search directed toward specific
goals. The search is made complex because of the need to determine the relevance of
information and because of the frequent occurrence of uncertain and ambiguous data.
Heuristics provide the A.I. system with a mechanism for focusing its attention and
controlling its searching processes. The necessarily adaptive organization of A.I.
systems yields the requirement for A.I. computational Architectures. All knowledge
utilized by the system must be represented within such an architecture. The acquisition
and encoding of real-world knowledge into A.I. architecture comprises the subfield of
Knowledge Engineering.
KEYWORDS – Artificial Intelligence, Machine Learning, Deep Learning, Encoding,
Subfield, Perception, Manipulation, Reasoning, Communication, and Learning.
Similar to Handwritten Recognition using Deep Learning with R (20)
Malaysia R User Group Meetup at Microsoft Malaysia, 13th July 2017. Facebook Page https://www.facebook.com/rusergroupmalaysia/
Video of the talk can be viewed here https://www.youtube.com/watch?v=lN057ua0dKU
Explore and have fun with TensorFlow: An introductory to TensorFlowPoo Kuan Hoong
TensorFlow and Deep Learning Malaysia Meetup 6th July 2017 https://www.facebook.com/groups/TensorFlowMY and recorded video of the talk can be viewed here https://www.youtube.com/watch?v=EdMz3fwRFBc
Context Aware Road Traffic Speech Information System from Social MediaPoo Kuan Hoong
This project focuses on developing a mobile application that transmits real-time traffic state to motorcyclists. The traffic data is collected from Twitter. The data collected is subjected to various processes like Named Entity Recognition, Sentiment Analysis and Statistical Analysis and the derived traffic state will be transmitted to the user’s mobile application. A Bluetooth enabled helmet of a motorcyclist will then playback the traffic state to the user according to their location.
Virtual Interaction Using Myo And Google Cardboard (slides)Poo Kuan Hoong
This project focuses on developing a mobile application that integrates Google Cardboard and Myo Armband. The mobile application developed is an educational application that teaches users to write Japanese characters by getting users to trace the characters display on the phone screen. The users will air draw the letters while the Myo Armband will capture the gestures, send the data to the smartphones and display the drawn character on the screen.
A Comparative Study of HITS vs PageRank Algorithms for Twitter Users AnalysisPoo Kuan Hoong
Social Networks such as Facebook, Twitter, Google+
and LinkedIn have millions of users. These networks are constantly
evolving and it is a good source of information, both
explicitly and implicitly. The analysis of Social Network mainly
focuses on the aspect of social networking with an emphasis
on mapping relationships, patterns of interaction between user
and content information. One of the common research topics
focuses on the centrality measures where useful information of
the connected people in the social network is represented in
a graph. In this paper, we employed two link-based ranking
algorithms to analyze the ranking of the users: HITS (Hyperlink-
Induced Topic Search) and PageRank. We constructed Twitter
user retweet-relationship graph using 21 days worth of data.
Lastly, we compared the ranking sequence of the users in addition
to their followers count against the average and also whether
they are verified Twitter accounts. From the results obtained,
both HITS and PageRank showed a similar trend, and more
importantly highlighted the importance of the direction of the
edges in this work.
Towards Auto-Extracting Car Park Structures: Image Processing Approach on Low...Poo Kuan Hoong
There have been numerous interests in the area of detecting availability of car park bay using image processing techniques instead of utilizing expensive sensors. An area that has been neglected in doing so is the initial calibration of the image capturing device on the need to determine the car park structures. This paper proposes a technique that addresses this issue, using the limited processing capabilities of embedded systems. The results are promising, where in its current form, is semi-automated calibration for the car park structure detection and further enhancements can be made, to make it completely automated
Discovery of Twitter User Interestingness Based on Retweets, Reply Mentions a...Poo Kuan Hoong
With the rising popularity of social media such as Facebook, Twitter, Instagram and many more, sentiment classification for social media has become a hot research topic. There were many research studies conducted on Twitter as it is one of the most widely used social media. Previous studies have approached the problem as a tweet-level classification task where each tweet is classified as positive, negative or neutral. However, getting an overall sentiment might not be useful to a business organizations which are using Twitter for monitoring consumer opinion of their products/services. Instead, it is more useful to determine specifically which tweets where users are happy or unhappy about. This paper proposes the discovery of Twitter user level interestingness based on relationships such as retweets, reply-mentions and pure-mentions using Google's PageRank algorithm. We conducted experiments and compared the results with hard-marked results by seven annotators.
A Comparison of People Counting Techniques viaVideo Scene AnalysisPoo Kuan Hoong
Real-time human detection and tracking from video surveillance footages is one of the most active research areas in computer vision and pattern recognition. This is due to the widespread application from being able to do it well. One such application is the counting of people, or density estimation, where the two key components are human detection and tracking. Traditional methods such as the usage of sensors are not suitable as they are not easily integrated with current video surveillance systems. As video surveillance systems are currently prevalent in most places, using vision based people counting techniques will be the logical approach. In this paper, we compared the two commonly used techniques which are Cascade Classifier and Histograms of Gradients (HOG) for human detection. We evaluated and compared these two techniques with three different video datasets with three different setting characteristics. From our experiment results, both Cascade Classifier and HOG techniques can be used for people counting to achieve moderate accuracy results.
UiPath Test Automation using UiPath Test Suite series, part 3DianaGray10
Welcome to UiPath Test Automation using UiPath Test Suite series part 3. In this session, we will cover desktop automation along with UI automation.
Topics covered:
UI automation Introduction,
UI automation Sample
Desktop automation flow
Pradeep Chinnala, Senior Consultant Automation Developer @WonderBotz and UiPath MVP
Deepak Rai, Automation Practice Lead, Boundaryless Group and UiPath MVP
Let's dive deeper into the world of ODC! Ricardo Alves (OutSystems) will join us to tell all about the new Data Fabric. After that, Sezen de Bruijn (OutSystems) will get into the details on how to best design a sturdy architecture within ODC.
GraphRAG is All You need? LLM & Knowledge GraphGuy Korland
Guy Korland, CEO and Co-founder of FalkorDB, will review two articles on the integration of language models with knowledge graphs.
1. Unifying Large Language Models and Knowledge Graphs: A Roadmap.
https://arxiv.org/abs/2306.08302
2. Microsoft Research's GraphRAG paper and a review paper on various uses of knowledge graphs:
https://www.microsoft.com/en-us/research/blog/graphrag-unlocking-llm-discovery-on-narrative-private-data/
"Impact of front-end architecture on development cost", Viktor TurskyiFwdays
I have heard many times that architecture is not important for the front-end. Also, many times I have seen how developers implement features on the front-end just following the standard rules for a framework and think that this is enough to successfully launch the project, and then the project fails. How to prevent this and what approach to choose? I have launched dozens of complex projects and during the talk we will analyze which approaches have worked for me and which have not.
JMeter webinar - integration with InfluxDB and GrafanaRTTS
Watch this recorded webinar about real-time monitoring of application performance. See how to integrate Apache JMeter, the open-source leader in performance testing, with InfluxDB, the open-source time-series database, and Grafana, the open-source analytics and visualization application.
In this webinar, we will review the benefits of leveraging InfluxDB and Grafana when executing load tests and demonstrate how these tools are used to visualize performance metrics.
Length: 30 minutes
Session Overview
-------------------------------------------
During this webinar, we will cover the following topics while demonstrating the integrations of JMeter, InfluxDB and Grafana:
- What out-of-the-box solutions are available for real-time monitoring JMeter tests?
- What are the benefits of integrating InfluxDB and Grafana into the load testing stack?
- Which features are provided by Grafana?
- Demonstration of InfluxDB and Grafana using a practice web application
To view the webinar recording, go to:
https://www.rttsweb.com/jmeter-integration-webinar
The Art of the Pitch: WordPress Relationships and SalesLaura Byrne
Clients don’t know what they don’t know. What web solutions are right for them? How does WordPress come into the picture? How do you make sure you understand scope and timeline? What do you do if sometime changes?
All these questions and more will be explored as we talk about matching clients’ needs with what your agency offers without pulling teeth or pulling your hair out. Practical tips, and strategies for successful relationship building that leads to closing the deal.
Neuro-symbolic is not enough, we need neuro-*semantic*Frank van Harmelen
Neuro-symbolic (NeSy) AI is on the rise. However, simply machine learning on just any symbolic structure is not sufficient to really harvest the gains of NeSy. These will only be gained when the symbolic structures have an actual semantics. I give an operational definition of semantics as “predictable inference”.
All of this illustrated with link prediction over knowledge graphs, but the argument is general.
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf91mobiles
91mobiles recently conducted a Smart TV Buyer Insights Survey in which we asked over 3,000 respondents about the TV they own, aspects they look at on a new TV, and their TV buying preferences.
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...UiPathCommunity
💥 Speed, accuracy, and scaling – discover the superpowers of GenAI in action with UiPath Document Understanding and Communications Mining™:
See how to accelerate model training and optimize model performance with active learning
Learn about the latest enhancements to out-of-the-box document processing – with little to no training required
Get an exclusive demo of the new family of UiPath LLMs – GenAI models specialized for processing different types of documents and messages
This is a hands-on session specifically designed for automation developers and AI enthusiasts seeking to enhance their knowledge in leveraging the latest intelligent document processing capabilities offered by UiPath.
Speakers:
👨🏫 Andras Palfi, Senior Product Manager, UiPath
👩🏫 Lenka Dulovicova, Product Program Manager, UiPath
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered QualityInflectra
In this insightful webinar, Inflectra explores how artificial intelligence (AI) is transforming software development and testing. Discover how AI-powered tools are revolutionizing every stage of the software development lifecycle (SDLC), from design and prototyping to testing, deployment, and monitoring.
Learn about:
• The Future of Testing: How AI is shifting testing towards verification, analysis, and higher-level skills, while reducing repetitive tasks.
• Test Automation: How AI-powered test case generation, optimization, and self-healing tests are making testing more efficient and effective.
• Visual Testing: Explore the emerging capabilities of AI in visual testing and how it's set to revolutionize UI verification.
• Inflectra's AI Solutions: See demonstrations of Inflectra's cutting-edge AI tools like the ChatGPT plugin and Azure Open AI platform, designed to streamline your testing process.
Whether you're a developer, tester, or QA professional, this webinar will give you valuable insights into how AI is shaping the future of software delivery.
Transcript: Selling digital books in 2024: Insights from industry leaders - T...BookNet Canada
The publishing industry has been selling digital audiobooks and ebooks for over a decade and has found its groove. What’s changed? What has stayed the same? Where do we go from here? Join a group of leading sales peers from across the industry for a conversation about the lessons learned since the popularization of digital books, best practices, digital book supply chain management, and more.
Link to video recording: https://bnctechforum.ca/sessions/selling-digital-books-in-2024-insights-from-industry-leaders/
Presented by BookNet Canada on May 28, 2024, with support from the Department of Canadian Heritage.
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024Tobias Schneck
As AI technology is pushing into IT I was wondering myself, as an “infrastructure container kubernetes guy”, how get this fancy AI technology get managed from an infrastructure operational view? Is it possible to apply our lovely cloud native principals as well? What benefit’s both technologies could bring to each other?
Let me take this questions and provide you a short journey through existing deployment models and use cases for AI software. On practical examples, we discuss what cloud/on-premise strategy we may need for applying it to our own infrastructure to get it to work from an enterprise perspective. I want to give an overview about infrastructure requirements and technologies, what could be beneficial or limiting your AI use cases in an enterprise environment. An interactive Demo will give you some insides, what approaches I got already working for real.
3. Introduction
In the past 10 years, machine learning and Artificial Intelligence (AI) have shown
tremendous progress
The recent success can be attributed to:
Explosion of data
Cheap computing cost - CPUs and GPUs
Improvement of machine learning models
Much of the current excitement concerns a subfield of it called “deep learning”.
3
5. Neural Networks
Deep Learning is primarily about neural networks, where a network is an
interconnected web of nodes and edges.
Neural nets were designed to perform complex tasks, such as the task of placing
objects into categories based on a few attributes.
Neural nets are highly structured networks, and have three kinds of layers - an input,
an output, and so called hidden layers, which refer to any layers between the input and
the output layers.
Each node (also called a neuron) in the hidden and output layers has a classifier.
5
7. Neural Network: Forward Propagation
The input neurons first receive the data features of the object. After processing the
data, they send their output to the first hidden layer.
The hidden layer processes this output and sends the results to the next hidden layer.
This continues until the data reaches the final output layer, where the output value
determines the object’s classification.
This entire process is known as Forward Propagation, or Forward prop.
7
8. Neural Network: Backward Propagation
To train a neural network over a large set of labelled data, you must continuously
compute the difference between the network’s predicted output and the actual output.
This difference is called the cost, and the process for training a net is known as
backpropagation, or backprop
During backprop, weights and biases are tweaked slightly until the lowest possible cost is
achieved.
An important aspect of this process is the gradient, which is a measure of how much
the cost changes with respect to a change in a weight or bias value.
8
9. The 1990s view of what was wrong with
back-propagation
It required a lot of labelled training data
Almost all data is unlabeled
The learning time did not scale well
It was very slow in networks with multiple hidden layers.
It got stuck at local optima
These were often surprisingly good but there was no good theory
9
10. Deep Learning
Deep learning refers to artificial neural networks that are composed of many layers.
It’s a growing trend in Machine Learning due to some favorable results in applications
where the target function is very complex and the datasets are large.
10
11. Deep Learning: Benefits
Robust
No need to design the features ahead of time - features are automatically learned to be optimal for
the task at hand
Robustness to natural variations in the data is automatically learned
Generalizable
The same neural net approach can be used for many different applications and data types
Scalable
Performance improves with more data, method is massively parallelizable
11
12. Deep Learning: Weaknesses
Deep Learning requires a large dataset, hence long training period.
In term of cost, Machine Learning methods like SVMs and other tree ensembles are
very easily deployed even by relative machine learning novices and can usually get you
reasonably good results.
Deep learning methods tend to learn everything. It’s better to encode prior
knowledge about structure of images (or audio or text).
The learned features are often difficult to understand. Many vision features are also
not really human-understandable (e.g, concatenations/combinations of different
features).
Requires a good understanding of how to model multiple modalities with
traditional tools.
12
14. H2O Library
H2O is an open source, distributed, Java machine learning library
Ease of Use via Web Interface
R, Python, Scala, Spark & Hadoop Interfaces
Distributed Algorithms Scale to Big Data
Package can be downloaded from http://www.h2o.ai/download/h2o/r
14
16. H2O booklets
H2O reference booklets can be downwloaded from https://github.com/h2oai/h2o-3
/tree/master/h2o-docs/src/booklets/v2_2015/PDFs/online
16
17. MNIST Handwritten Dataset
The MNIST database consists of handwritten digits.
The training set has 60,000 examples, and the test set has 10,000 examples.
The MNIST database is a subset of a larger set available from NIST. The digits have
been size-normalized and centered in a fixed-size image
For this demo, the Kaggle pre-processed training and testing dataset were used. The
training dataset, (train.csv), has 42000 rows and 785 columns.
17
18. Demo
The sourcecode can be accessed from here
https://github.com/kuanhoong/myRUG_DeepLearning
18