https://blog.tensorflow.org/2019/02/mit-introduction-to-deep-learning.html?hl=ja

Education

https://3.bp.blogspot.com/-JYbNelUE66k/XhOdLxanW5I/AAAAAAAACVI/fD375RZr0BAtoosh-e5Zbzz-gEll6bmxwCLcBGAsYHQ/s1600/intro.png

2月 28, 2019 —
*Guest post by MIT 6.S191 Introduction to Deep Learning***MIT 6.S191: Introduction to Deep Learning is an introductory course offered formally at MIT and open-sourced on its course website. The class consists of a series of foundational lectures on the fundamentals of neural networks and their applications to sequence modeling, computer vision, generative models, and reinforcement learning.**MIT’s offi…

MIT Introduction to Deep Learning

MIT Introduction to Deep Learning lectures and labs are are open-source and free for everyone! |

MIT’s Introduction to Deep Learning consists of technical lectures on state-of-the-art algorithms as well as applied software labs in TensorFlow. |

All lectures are available online for free — click here to watch! |

This blog highlights each of these three software labs and their accompanying lectures.

Gain practical experience with in-depth TensorFlow software labs. |

Our introduction to TensorFlow exercises highlight a few key concepts in particular: how to

Following the Intro to TensorFlow module, Lab 1’s second module dives right into building and applying a

You’ll fill in code blocks to define the RNN model, train the model using a dataset of Irish folk songs (in the ABC notation), use the learned model to generate a new song, and then play back what’s generated to hear how well your model performs. Check out this example song we generated:

The second portion of this lab takes things a step further, and explores two prominent examples of applied deep learning: facial detection and algorithmic bias. Though it may be no surprise that neural networks perform really well at recognizing faces in images, there’s been a lot of attention recently on how some of this AI may suffer from hidden algorithmic bias. Actually, it turns out that

In recent work, we trained a model, based on a variational autoencoder (VAE), that learns both a specific task, like face detection, and the

This software lab is inspired by this work:

```
def debiasing_loss_func(x, x_pred, y_label, y_logit, z_mu, z_logsigma, kl_weight=0.005):
# compute loss components
reconstruction_loss = tf.reduce_mean(tf.keras.losses.MSE(x,x_pred), axis=(1,2))
classification_loss = tf.nn.sigmoid_cross_entropy_with_logits(labels=y_label, logits=y_logit)
kl_loss = 0.5 * tf.reduce_sum(tf.exp(z_logsigma) + tf.square(z_mu) - 1.0 - z_logsigma, axis=1)
# propogate debiasing gradients only on relevant datapoints
gradient_mask = tf.cast(tf.equal(y_label, 1), tf.float32)
# define the total debiasing loss as a combination of the three losses
vae_loss = kl_weight * kl_loss + reconstruction_loss
total_loss = tf.reduce_mean(classification_loss + gradient_mask * vae_loss)
return total_loss
```

Importantly, this approach can be applied Compared to previous labs which focused on supervised and unsupervised learning, reinforcement learning seeks to teach an agent how to act in the world to maximize its own reward. Tensorflow’s imperative execution provides a streamlined method for RL which students program from the ground-up in Lab 3.

We focus on learning two tasks in both control (e.g. Cart-Pole) and games (e.g. Pong). Students were tasked in building a modular RL framework to learn these two very different environments using only a single “RL brain”.

Dealing with these baseline environments provides students with a fast way to quickly prototype new algorithms, get a concrete understanding of how to implement RL training procedures, and use these ideas as templates moving forward in their final projects.

Next post

Education
**·**

MIT Introduction to Deep Learning

2月 28, 2019
—
*Guest post by MIT 6.S191 Introduction to Deep Learning***MIT 6.S191: Introduction to Deep Learning is an introductory course offered formally at MIT and open-sourced on its course website. The class consists of a series of foundational lectures on the fundamentals of neural networks and their applications to sequence modeling, computer vision, generative models, and reinforcement learning.**MIT’s offi…

Build, deploy, and experiment easily with TensorFlow