AI, Machine Learning And Deep Learning: An Overview
AI is a general field that encompasses machine learning and deep learning, but also includes many more approaches that don’t involve any learning”.For example, the precursor to today's chatbots, ELIZA, which was created in the MIT Artificial Intelligence Laboratory. This program could maintain a long dialogue with a person, but could not learn new words or correct its behavior during a dialogue. The behavior of ELIZA was to be specified explicitly using a special programming language.
The history of artificial intelligence in its modern sense begins in the 1950s, with the works of Alan Turing and the Dartmouth workshop, which brought together the first enthusiasts of this field and in which the basic principles of the science of AI were formulated. Further, this industry experienced several cycles of a surge of interest and subsequent recessions (the so-called “AI winters”), in order to become one of the key areas of world science today.
Over the past few years AI has exploded, and especially since 2015. Much of that has to do with the wide availability of GPUs that make parallel processing ever faster, cheaper, and more powerful.Nowadays, it’s hard to imagine any type of activity without AI in use. Whether you drive a car, take selfies, pick up sneakers for yourself in an online store or plan a vacation, almost everywhere you are assisted by a small, weak, but already very useful artificial intelligence.One of the key features of intelligence (artificial and not really artificial) is the ability to learn.
What is Machine Learning?
Features and components of Machine Learning
Learning is the process of gaining understanding by constructing models of observed data with the intention to use them for prediction. More data is added & used by the algorithm, the performance of the system improves.
Examples/Benefits of Real Time Machine Learning
The importance of Machine Learning is being accelerated with the emergence of ‘Era of Analytics’, for its key benefits – Scalable, Custom Built, Real Time & Quick, Automated, Accurate and Efficient.
Machine Learning is an important filed of computer science with its advent based on the research of pattern recognition. Once the pattern recognition is done it is used to generate a computational learning in artificial intelligence. Machine learning can be defined as a type or a branch of a big tree - artificial intelligence (AI) that mainly gives computerized systems with ability by which they can uniquely learn on their own without being explicitly programmed. Focus in Machine learning is on the development of computer programs that can change when exposed to new data. The process of machine learning is quite similar to that of data mining. Both systems search through enormous amount of data to look for patterns. However, instead of extracting data for human comprehension -- as is the case in data mining applications – data patterns are detected in data using machine learning and adjust program actions accordingly to increase the efficiency. Machine learning algorithms are mainly categorized in two types as being supervised or unsupervised. Supervised algorithms can apply what has been learned in the past to new data. Unsupervised algorithms can draw inferences from data sets. This field is mainly developed from the study of pattern and data recognition theory in artificial intelligence, machine learning is a branch of AI that explores the study, structure and construction of those unique algorithms which can learn from the output of previous result sets and make calculated predictions on data.
There are three main categories of machine learning:
- Supervised learning - the system is trained on the basis of data examples with previously known results for each example. There are two most popular tasks for machine learning: the regression and the classification task. Regression is a prediction of a continuous outcome, such as the price of a house or the level of manufacturing emissions. Classification - a category (class) prediction, for example, whether an email is a spam or not, whether the book is a detective novel or an encyclopedia.
- Unsupervised learning - the system finds internal relationships and patterns in the data. In this case, the results for each example are unknown.
- Reinforcement learning is an approach in which the system is rewarded for correct actions and penalized for wrong ones. As a result, the system learns to develop an algorithm in which it receives the highest reward and the lowest penalty.
Where exactly is machine learning used?
In today’s world, Machine Learning is used almost everywhere. Your own personalized Facebook feed which you see, the ability to recognize your photos on Facebook photo albums so that Facebook automatically tags them, Recommendations for movies on Hotstar are some of the applications of Machine Learning. Basically, machine learning algorithms are mainly employed in a wide number of tasks that require computational power and calculations where designing and data programming methods don’t work.
Machine learning is tight coupled with statistics to compute, which helps in predicting. The foot prints of Machine learning are huge in cases where the programming is infeasible as the numbers of cases to be dealt would be infinite.Machine learning has the capability of driving computers to decide and take an action based on the result set and the actions are learnt but they are not explicitly programmed.
Deep learning refers to a set of techniques by which we can achieve varying degrees of artificial intelligence by mimicking the working of a human brain. Deep learning is a subset of Machine Learning techniques that aim to achieve Artificial Intelligence.The distinguishing feature of Deep Learning is its use of various Artificial Neural Networks, that imitate the human brain. Just as in the brain, Artificial Neural Networks or ANNs also consist of neurons and synapses between them.
Deep Learning and Machine Learning:
Earlier AI systems were using the pattern to match and expert systems. The core idea behind machine learning is that the machine itself learn and respond without human intervention. Whereas, Deep Learning is the breakthrough innovation in the field of artificial intelligence. Deep learning is actually a subset of machine learning. It technically is machine learning and functions in the same way but it has different capabilities.
The main difference between deep and machine learning is, machine learning models become better progressively but the model still needs some guidance. If a machine learning model returns an inaccurate prediction then the programmer needs to fix that problem explicitly but in the case of deep learning, the model does it by himself. Automatic car driving system is a good example of deep learning.In traditional Machine Learning, the data must be broken down into individual features. These hand-crafted features are fed into the model and we get a prediction as an output. However, hand-crafting features is a time-consuming process that involves a lot of statistical knowledge and expertise in data science.
With the advent of Deep Learning and multi-layered Artificial Neural Networks, feature selection can now be handled by the model itself. By feeding it numerical representation of raw data (Images, Video, Audio etc), the multi-layered architecture allows for the model to determine the highest-contributing features and uses them to make successful predictions, without any human crafted features. This drastically shortened project timelines and human intervention in the preliminary stages. A small caveat is that DL models required larger volumes of data to train than traditional ML models.
How Deep Learning Works
If I give you images of horses, you recognize them as horses, even if you’ve never seen that image before. And it doesn’t matter if the horse is lying on a sofa, or dressed up for Halloween as a hippo. You can recognize a horse because you know about the various elements that define a horse: shape of its muzzle, number and placement of legs, and so on.
Deep learning can do this. And it’s important for many things including autonomous vehicles. Before a car can determine its next action, it needs to know what’s around it. It must be able to recognize people, bikes, other vehicles, road signs, and more. And do so in challenging visual circumstances. Standard machine learning techniques can’t do that.
Take natural language processing, which is used today in chatbots and smartphone voice assistants, to name two. Consider this sentence and work out what the last part should be:I was born in Italy and, although I lived in Portugal and Brazil most of my life, I still speak fluent ________.Hopefully you can see that the most likely answer is Italian (though you would also get points for French, Greek, German, Sardinian, Albanian, Occitan, Croatian, Slovene, Ladin, Latin, Friulian, Catalan, Sardinian, Sicilian, Romani and Franco-Provencal and probably several more). But think about what it takes to draw that conclusion. First you need to know that the missing word is a language. You can do that if you understand “I speak fluent…”. To get Italian you have to go back through that sentence and ignore the red herrings about Portugal and Brazil. “I was born in Italy” implies learning Italian as I grew up (with 93% probability according to Wikipedia), assuming that you understand the implications of born, which go far beyond the day you were delivered. The combination of “although” and “still” makes it clear that I am not talking about Portuguese and brings you back to Italy. So Italian is the likely answer.Imagine what’s happening in the neural network in your brain. Facts like “born in Italy” and “although…still” are inputs to other parts of your brain as you work things out. And this concept is carried over to deep neural networks via complex feedback loops.
A great example of deep learning is Google’s AlphaGo. Google created a computer program with its own neural network that learned to play the abstract board game called Go, which is known for requiring sharp intellect and intuition. By playing against professional Go players, AlphaGo’s deep learning model learned how to play at a level never seen before in artificial intelligence, and did without being told when it should make a specific move (as a standard machine learning model would require). It caused quite a stir when AlphaGo defeated multiple world-renowned “masters” of the game—not only could a machine grasp the complex techniques and abstract aspects of the game, it was becoming one of the greatest players of it as well.
Advantages of studying Deep Learning:
Deep learning is a buzz-word, synonymous with cutting edge Artificial Intelligence. Whether it’s Waymo’s self driving car, OpenAI’s DoTA playing AI or digital smart assistants like Siri or Alexa, the impact that deep learning has had on modern day technology is significant.Let us discuss some of the advantages studying deep learning.
1) Data-Driven Everything - Deep Learning can be applied to ANY domain at some capacity, so long as there are volumes of data generated to train the models.
2) Highly Accessible - Advancements in software, hardware and the open-source community of Deep Learning Practitioners have made DL the most accessible it’s ever been since its inception.
Deep learning Frameworks
A deep learning framework is an interface, library or a tool which allows us to build deep learning models more easily and quickly, without getting into the details of underlying algorithms. They provide a clear and concise way for defining models using a collection of pre-built and optimized components. Below is comparison table of some of the Deep Learning frameworks.
All of these frameworks are open source, support CUDA and have pretrained models to help you get started.
Conclusion
Deep learning has enabled many practical applications of machine learning and by extension the overall field of AI. Deep learning breaks down tasks in ways that makes all kinds of machine assists seem possible, even likely. Driverless cars, better preventive healthcare, even better movie recommendations, are all here today or on the horizon. AI is the present and the future. With Deep learning’s help, AI may even get to that science fiction state we’ve so long imagined. Artificial intelligence is a general area of automation of intellectual tasks (such as reading, playing Go, image recognition, and creating self-driving cars). Machine learning is a set of artificial intelligence methods that are responsible for the ability of an AI to learn. Deep learning is a subclass of machine learning methods that study multi-layer neural networks.
https://www.youtube.com ? watch ? v=WSbgixdC9g8
https://www.youtube.com/watch?v=q7bKMHdxtPU