Let’s look at one more interesting thing. I mentioned before that one of the purposes of this example was to examine and visualize our eigenfaces, as they are called: our super columns. I will not disappoint. Let’s write some code that will show us our super columns as they would look to us humans: def […]
We have gathered 1,288 images of people’s faces, and each one has 1,850 features (pixels) that identify that person. Here’s the code we used – an example of one of our faces can be seen in Figure 11.22:plt.imshow(X[100].reshape((h, w)), cmap=plt.cm.gray) lfw_people.target_names[y[100]] ‘George W Bush’ Figure 11.22 – A face from our dataset: George W. Bush […]
Our goal is to predict whether or not a person gave a 5- or 1-star review based on the words they used in the review. Let’s set a baseline with logistic regression and see how well we can predict this binary category:from sklearn.linear_model import LogisticRegression lr = LogisticRegression()X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=100) […]
Put another way, the COD states that as we increase the number of feature columns, we need exponentially more data to maintain the same level of model performance. This is because, in high-dimensional spaces, even the nearest neighbors can be very far away from a given data point, making it difficult to create good predictions. […]
Feature extraction and PCA A common problem when working with data, particularly when it comes to ML, is having an overwhelming number of columns and not enough rows to handle such a quantity of columns. A great example of this is when we were looking at the send cash now example in our naïve Bayes […]
Understanding pre-trained models Pre-trained models are like learning from the experience of others. These models have been trained on extensive datasets, learning patterns, and features that make them adept at their tasks. Think of it as if a model has been reading thousands of books on a subject, absorbing all that information. When we use […]
Decoding BERT’s pre-training One of the most impressive feats of TL can be observed in BERT, a pre-trained model that revolutionized the NLP landscape. Two fundamental training tasks drive BERT’s robust understanding of language semantics and relationships: masked language modeling (MLM) and next sentence prediction (NSP). Let’s break them down and see how each one […]
Different types of TL Let’s take a moment to get familiar with the diverse landscape of TL. It’s not a single monolithic idea, but rather a collection of varied strategies that fall under one umbrella term. There’s a type of TL for just about every scenario you might come across. Inductive TL First up, we […]
TL with BERT and GPT Having grasped the fundamental concepts of pre-trained models and TL, it’s time to put theory into practice. It’s one thing to know the ingredients; it’s another to know how to mix them into a delicious dish with them. In this section, we will take some models that have already learned […]
Example – TL for image classification We could take a pre-trained model such as ResNet or the Vision Transformer (shown in Figure 12.10), initially trained on a large-scale image dataset such as ImageNet. This model has already learned to detect various features from images, from simple shapes to complex objects. We can take advantage of […]
