3. DATA USED:
TRAIN & TEST
TASK: Image Classification
• Training Set: 25,000 images
• Test Set: 12,500 images
4. DEEP LEARNING
Deep learning is a class of machine learning algorithms that:
use a cascade of multiple layers of nonlinear processing units for feature extraction and
transformation. Each successive layer uses the output from the previous layer as input.
learn in supervised (e.g., classification) and/or unsupervised (e.g., pattern analysis) manners.
learn multiple levels of representations that correspond to different levels of abstraction; the levels
form a hierarchy of concepts.
5. WHY DEEP LEARNING?
Deep Learning out perform other techniques if the data size is large. But with
small data size, traditional Machine Learning algorithms are preferable.
Deep Learning really shines when it comes to complex problems such as
image classification, natural language processing, and speech recognition.
6. RANDOM FOREST
Random forests or random decision forests are an ensemble learning method
for classification, regression and other tasks, that operate by constructing a multitude
of decision trees at training time and outputting the class that is the mode of the classes
(classification) or mean prediction (regression) of the individual trees.
Random decision forests correct for decision trees' habit of over fitting to their training set.
7. MODEL USED:
DEEP NEURAL NETWORK
A Deep Neural Network (DNN) is an artificial neural network (ANN) with multiple
layers between the input and output layers.
The network moves through the layers calculating the probability of each output.
For example, a DNN that is trained to recognize dog and cat brees will go over
the given image and calculate the probability that the cat or dog in the image is
the certain breed.
8. DNN CLASSIFIER
Deep Neural Networks are able to adapt to more complex datasets and better generalize to
previously unseen data primarily due to its multiple layers, hence why they’re called deep.
These layers allow them to fit more complex datasets than linear models can.
However, the tradeoff is that the model will tend to take longer to train, be larger in size, and
have less interpretability. So why would anyone want to use it? Because it can lead to higher
final accuracies.