분류 전체보기 (248) 썸네일형 리스트형 [Lesson 4] Going Further with CNNs (1) - In the previous lesson, we built and trained a CNN to classify small grayscale images of articles of clothing from the fashon MNIST dataset. - One of the great advantage of CNN's is that they can also work with color images. - Later in the lesson, I'll build and train a convolutional neural network, that can classify color images of cats and dogs. - Along the way, I'll also learn different tec.. Deep Learning 개론 (서강대 강석주 교수) ※강연을 들으며 정리한 내용입니다. Introduction to Research Topics Introduction to Deep Learning Deep Learning Techniques and Applications - 연구실 연구 분야 : Computer Vision Software Application & Realistic Display Hardware Application - 세부 연구 내용 딥러닝 기반 FPGA 하드웨어 구조 및 설계 연구 360도 VR 영상 획득 및 카메라 기술 연구 딥러닝 기반 차량 모니터링 시스템 개발 연구 딥러닝 기반 영상 처리 알고리즘 개발 연구 - 머신러닝의 종류 3가지 Supervised Learning(지도학습) Unsupervised Learning(비지도학습.. [Lesson 3] Introduction to CNNs (2) - We just learned about convolutions and max pooling. Convolution is the process of applying a filter (“kernel”) to an image. Max pooling is the process of reducing the size of the image through downsampling. - Convolutional layers can be added to the neural network model using the Conv2D layer type in Keras. This layer is similar to the Dense layer, and has weights and biases that need to be tu.. [Lesson 3] Introduction to CNNs (1) - In the previous lesson, we saw how we can build and train a deep neural network to classify images of articles of clothing using the Fashion-MNIST dataset. - CNNs have proven to achieve higher accuracies when classifying images than the symbol period dense neural networks we saw in the previous lessons. - In this lesson, we will see how easy it is to create a CNN-based image classifier from sc.. [Lesson 2] Your First Model: Fashion MNIST (2) - When training a Machine Learning model, I always need to split my data set into at least two different partitions, the data I use for training, and the data I use for testing. - We want to test it on data that it hasn't seen before, to see how well it performs. - If we did not do this, we wouldn't know if the neural network has decided to memorize the images it saw during trainig. - TensorFlow.. [Lesson 2] Your First Model: Fashion MNIST (1) - In the previous lesson, I got a quick look at how to build and train neural networks using TensorFlow and Keras, and how neural networks and the training process works. - In this lesson, I will create a neural network that can recognize items of clothing and images. - Remember, an example is a feature(inputs) label(outputs) pair that I feed to the training loop. - The Fashion-MNIST dataset con.. [Lesson 1] Introduction to Machine Learning (2) - This was really impressive considering that we only needed a few lines code: 1) l0 = tf.keras.layers.Dense(units=1, input_shape=[1]) 2) model = tf.keras.Sequential([l0]) 3) model.compile(loss='mean_squared_error', optimizer=tf.keras.optimizers.Adam(0.1)) 4) history = model.fit(celsius_q, fahrenheit_a, epochs=500, verbose=False) 5) model.predict([100.0]) - This example is the general plan for o.. [Lesson 1] Introduction to Machine Learning (1) - There are many types of neural network architectures. However, no matter what architecture you choose, the math it contains (what calculations are being performed, and in what order) is not modified during training. - Instead, it is the internal variables (“weights” and “biases”) which are updated during training. ex) F= C * ? + ? - The machine learning approach consists of using a neural netw.. 이전 1 ··· 25 26 27 28 29 30 31 다음
