How Can I Teach My Machine to Learn
Like humans, machines learn from experience. They make observations from inputs of images, text, or other data, and then look for patterns. After the machine runs through the mathematical layers, it learns to make better decisions based on the examples it was given. The decision outputs can be continuous (for example, fluctuating prices), binary (yes or no), or categorical (such as recognizing an aircraft, tank, helicopter, or submarine). In the case of a categorical output, the resulting answer will be several variables (for example, attributes that describe the aircraft) instead of a single variable.
The training environment for machine learning applications will roughly fit into one of three major categories: supervised learning, unsupervised learning, or reinforced learning. In this white paper, we will look at both supervised and unsupervised learning, plus the hybrid approach of semi-supervised learning.
Login and download this white paper to learn more about:
- Supervised, unsupervised, and semi-supervised approaches to machine learning
- Accuracy and trade-offs of different approaches
- Classification algorithms
- Regression analysis
- Dimensionality reduction
- Associated rules analysis
- Machine learning frameworks, including TensorFlow, Keras, PyTorch, MXNet and Gluon, and Caffe
- Hardware foundations for machine learning, including embedded computing modules and small form factor (SFF) system solutions
Login to download this resource