Wide & Deep Learning with TensorFlow – Machine Learning

and Deep learning combines the power
of memorization and generalization,
and it does that by jointly training
widening your models and deepening your networks. We’re sharing a
research paper about it and also the implementation
with an easy-to-use API in TensorFlow, which is an open
source library for a machine intelligence. So you might wonder what Wide
and Deep learning is good for. Wide and Deep learning is
useful for generic large scale regression and classification
problems with sparse inputs, things like recommendation
systems, search, and ranking problems. Now imagine you wanted to
build a search engine for food. Given a query, you want
to recommend the items that your users
will like the most. Using widening your
models, you can actually use a wide set of cross-product
features transformations to memorize specific
feature combinations. An example would be
when the users say the query, “fried
chicken,” your model might memorize that
chicken and waffles is more relevant than
chicken fried rice. But one limitation
is that it’s actually hard to generalize to
previously unseen combinations without manual
feature engineering. So instead, using
deep neuronetworks, you can now generalize better
through lower dimension embeddings. For example, your model might
learn to recommend burgers given the query, “fried
chicken,” because they are similar types of food. However, sometimes memorizing
specific combinations as rules and exceptions
is very important. When people ask for
iced decaf latte, you don’t really want to
overgeneralize and give them hot latte no matter
how close they are in the embedding space. So by jointly training
Wide and Deep models, we actually allow
them to complement each other’s strengths
and weaknesses. MUSTAFA IPSIR: To help
developers get started, we released Wide and Deep
as part of the TF Learn API. TF Learn is a high level
machine learning library on top of TensorFlow. The API helps users focus
on the important questions like, how will you
design your features, and what is your
model structure? You can create a Wide
and Deep classifier with just a few lines of code. Then you specify
the features you use in the widening model
and the deep neuronetworks, and we handle the joint
training under the hood. There are different
needs and requirements from Deep learning networks
and Wide [INAUDIBLE] models. We found a way to balance this. We provide a simple feature
engineering interface that lets you
specify embeddings, crosses, and
bucketization easily. For example, to learn
the relationship between a specific query
and a specific item, you can define across columns
with a single line of code. Similarly, to learn
generalization, you can define an
embedding column with a single line of code. HENG-TZE CHENG:
So to get started, we encourage developers to
check out our blog posts in the description, which links
to our tutorials, code samples, and our research paper. We really hope more
and more people will find these
useful in their work and explore the possibilities of
Wide and Deep Learning with us.


  1. Mercuric redRoad

    June 29, 2016 at 5:51 pm

    So impressive!

  2. TheYBooks

    June 29, 2016 at 8:39 pm

    what kind of background is needed to start with machine learning ?

  3. Hui Lin

    June 30, 2016 at 1:29 am


  4. kaushik raghupathruni

    June 30, 2016 at 3:45 am


  5. tamuka chikanyairo

    June 30, 2016 at 3:55 pm

    can someone give me the links for materials to get started with machine learning and deep learning please or feel free to send me resources at [email protected]

  6. Wu Peter

    July 1, 2016 at 3:52 pm

    凤凰大视野 (2016年06月29日) 风向北吹——北伐战争90周年回望(三)

  7. Baran Kaynak

    July 7, 2016 at 12:50 am

    Hello Mustafa İspir. I am proud of to see a Turk in this video. I wish you to get more success…

  8. Siraj Raval

    July 19, 2016 at 11:29 pm

    Hell yeah! If you guys like machine learning check out my new ML series on my channel.

  9. 简丹

    November 17, 2016 at 2:53 pm

    I get this error when i try to run the existing wide_n_deep_tutorial.py, any ideas on this?

    (tensorflow) [email protected]:~$ python wide_n_deep_tutorial.py –model_type=wide_n_deep

    Traceback (most recent call last):
    File "wide_n_deep_tutorial.py", line 208, in <module>
    File "/xxxxxxx/anaconda2/envs/tensorflow/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 30, in run
    File "wide_n_deep_tutorial.py", line 204, in main
    File "wide_n_deep_tutorial.py", line 196, in train_and_eval
    m = build_estimator(model_dir)
    File "wide_n_deep_tutorial.py", line 80, in build_estimator
    gender = tf.contrib.layers.sparse_column_with_hash_bucket(
    AttributeError: 'module' object has no attribute 'sparse_column_with_hash_bucket'

    I have no problems with TF installation, and my tensorflow version is 0.9 ,python 2.7 .Last week,the text_cnn.py examples run just fine.

  10. estudading electronica

    July 26, 2017 at 2:03 am

    y los subtitulos en español?

  11. Rankz

    June 19, 2019 at 11:32 am

    I like how the background music gives the illusion that this explanation is simple.

Leave a Reply