Hello everyone!!! Welcome to Learnaholic India. Today we are going to see difference between machine learning and deep learning. The topics today we are gonna cover are What is machine learning? What is deep learning? Machine learning process, Deep learning process, Difference between machine learning and deep learning and when to use machine learning or deep learning? So without wasting a time lets start with what is machine learning? Machine learning is the field of study that gives computers the capability to learn without being explicitly programmed. Machine learning is one of the most exciting technologies that one would have ever come across. As it is evident from the name, it gives the computer that which makes it more similar to humans: The ability to learn. Machine learning is actively being used today, perhaps it is used in many places. Machine learning is the best tool so far to analyze, understand and identify a pattern in the data One of the main ideas behind machine learning is that the computer can be trained to automate task that would be exhaustive or impossible for a human being. The clear breach from the traditional analysis is that machine learning can take decisions with minimal human intervention. Machine learning uses data to feed an algorithm that can understand the relationship between the input and the output. When the machine finished learning, it can predict the value or the class of new data point. What is Deep Learning? Deep learning is a branch of machine learning which is completely based on artificial neural network. Neural network is going to mimic the human brain so deep learning is also a kind of mimic of human brain. Deep learning is a subset of machine learning and it is called as deep learning because it makes use of deep neural networks. The machine uses different layers to learn from the data. The depth of the model is represented by the number of layers in the model. Deep learning is the new state of the art in term of AI. In deep learning, the learning phase is done through a neural network. A neural network is an architecture where the layers are stacked on top of each other. Now we will see machine learning process. Imagine you are meant to build a program that recognizes objects To train the model, you will use a classifier. A classifier uses the features of an object to try identifying the class it belongs to. For example, the classifier will be trained to detect if the image is a: Bicycle,Boat,Car
or a Plane This four objects above mentioned are the class that are classifier which we have to recognize. To construct a classifier, you need to have some data as input and assigns a label to it. The algorithm will take these data, to find a pattern and then classify it in the corresponding class. This is the task which is called supervised learning. In supervised learning, the training data you feed to the algorithm includes a label. The training, to train an algorithm requires to follow a few standard steps that are: Collect the data,Train the classifier and make the predictions. The first step is necessary, choosing the right data will make the algorithm success or a failure. The data you choose to train the model is called a feature. In the object example, the features are the pixels of the images. Each image is a row in the data while each pixel is a column. The objective is to use these training data to classify the type of object. The first step consists of creating the feature columns. Then, the second step involves choosing an algorithm to train the model. When the training is done, the model will predict what picture corresponds to what object. After that, it is easy to use the new model to predict new images. For each new image feeds into the model, the machine will predict the class it belongs to. For example, an entirely new image without a label is going through the model. For a human being, it is trivial to visualize the image as a car. The machine uses its previous knowledge to predict as well the image is a car. no we will see deep learning process. In deep learning, the learning phase is done through a neural network. A neural network is an architecture where the layers are stacked on top of each other. Consider the same example above. For that we have to mention where the image is car, or a bicycle or a boat or a plane. The training set would be fed to a neural network. Each input goes into a neuron and is multiplied by a weight. The result of the multiplication flows to the next layer and become the input. This process is repeated for each layer of the network. The final layer is named the output layer; it provides an actual value for the regression task and a probability of each class for the classification task. The neural network uses a mathematical algorithm to update the weights of all the neurons. The neural network is fully trained when the value of the weights gives an output close to the reality. For instance, a well-trained neural network can recognize the object on a picture with higher accuracy than the traditional neural network. Now lets see the difference between machine learning and deep learning. There are five points on the basis of we can differentiate between machine learning and deep learning. First is data dependencies. In machine learning excellent performances on a small or medium data-set. where as in deep learning excellent performances are carried out on a big data-set. The second point is hardware dependencies. In machine learning, the work on a low end machine, where as in deep learning, it requires a powerful machine. Preferably with GPU i.e. general processing unit. The deep learning performs a significant amount of matrix multiplication The next point is feature engineering. Where in machine learning, you need to understand a feature which represents the data. and in deep learning, there is no need to understand the best feature that represents the data. The four point is execution time. In machine learning, the execution time flows from few minutes to multiple or couple of hours. Where as in deep learning, the execution time is upto weeks also. Neural Network needs to compute a significant number of weights. The last point is interpretability. In machine learning, some algorithms are easy to interpret. for example, logistic regression, decision tree. and some algorithm are almost impossible. For example, SVM or XGSBoost i.e. these are the algorithms which are impossible to implement. where as in learning, it is difficult to impossible for inter-ability. The next point is when to use ML or DL? The following table, there are difference between ML and DL according to the training data set feature selection, number of algorithm used or/and the training time. So for the training data set, the machine learning dataset should be small. For deep learning, it should be large. For feature selection, ML does feature selection but in deep learning there no feature selection. There is calculations of weight. The next is number of algorithm. In ML there are many algorithms are used but in deep learning very few algorithms are used. In ML, training time is short. where as in deep learning the training time is long. That’s all for today, always remember sharing of knowledge is gaining of knowledge. Thank you for watching today’s session. If you are new to this channel then subscribe to Learnaholic India and don’t forget to click on the bell icon for latest video updates. If you like today’s video then like it, share it with your friends also if you have any query then please comment below. That’s it for today. Stay tuned for next video. Thank you!!!